German AI Competence Centers
The Network of the German AI Competence Centers
Our Collaborations With the German AI Competence Centers
The MCML has enjoyed fruitful collaborations with the other German AI Competence Centers, reflecting the growing importance of interdisciplinary teamwork in advancing the field of AI. These partnerships have resulted in a series of impactful publications, showcasing the breadth and depth of research being carried out across various domains within AI.
The study introduces a novel method for improving text-to-image (T2I) models by optimizing the initial noise using human preference reward models. This approach significantly enhances T2I model performance, outperforming existing open-source models and achieving efficiency and quality levels comparable to proprietary systems.
ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization.
NeurIPS 2024 - 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. URL GitHub
Abstract
Text-to-Image (T2I) models have made significant advancements in recent years, but they still struggle to accurately capture intricate details specified in complex compositional prompts. While fine-tuning T2I models with reward objectives has shown promise, it suffers from ‘reward hacking’ and may not generalize well to unseen prompt distributions. In this work, we propose Reward-based Noise Optimization (ReNO), a novel approach that enhances T2I models at inference by optimizing the initial noise based on the signal from one or multiple human preference reward models. Remarkably, solving this optimization problem with gradient ascent for 50 iterations yields impressive results on four different one-step models across two competitive benchmarks, T2I-CompBench and GenEval. Within a computational budget of 20-50 seconds, ReNO-enhanced one-step models consistently surpass the performance of all current open-source Text-to-Image models. Extensive user studies demonstrate that our model is preferred nearly twice as often compared to the popular SDXL model and is on par with the proprietary Stable Diffusion 3 with 8B parameters. Moreover, given the same computational resources, a ReNO-optimized one-step model outperforms widely-used open-source models such as SDXL and PixArt-α, highlighting the efficiency and effectiveness of ReNO in enhancing T2I model performance at inference time.
MCML Authors
Shyamgopal Karthik
Interpretable and Reliable Machine Learning
The paper introduces a new benchmark, FoMo-in-Flux, for continual multimodal pretraining, designed to tackle the challenges of updating multimodal foundation models. The guide provides practical advice for practitioners on how to update models effectively and efficiently in real-world applications..
A Practitioner's Guide to Real-World Continual Multimodal Pretraining.
NeurIPS 2024 - 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. URL GitHub
Abstract
Multimodal foundation models serve numerous applications at the intersection of vision and language. Still, despite being pretrained on extensive data, they become outdated over time. To keep models updated, research into continual pretraining mainly explores scenarios with either (1) infrequent, indiscriminate updates on large-scale new data, or (2) frequent, sample-level updates. However, practical model deployment often operates in the gap between these two limit cases, as real-world applications often demand adaptation to specific subdomains, tasks or concepts – spread over the entire, varying life cycle of a model. In this work, we complement current perspectives on continual pretraining through a research test bed as well as provide comprehensive guidance for effective continual model updates in such scenarios. We first introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements, constructed over 63 datasets with diverse visual and semantic coverage. Using FoMo-in-Flux, we explore the complex landscape of practical continual pretraining through multiple perspectives: (1) A data-centric investigation of data mixtures and stream orderings that emulate real-world deployment situations, (2) a method-centric investigation ranging from simple fine-tuning and traditional continual learning strategies to parameter-efficient updates and model merging, (3) meta learning rate schedules and mechanistic design choices, and (4) the influence of model and compute scaling. Together, our insights provide a practitioner’s guide to continual multimodal pretraining for real-world deployment.
MCML Authors
The comprehensive review addresses the growing need for transparency in AI applications, especially in critical fields such as geospatial data analysis. The paper highlights methods, objectives, challenges, and findings, providing a much-needed summary of the state of XAI in this specialized area.
Opening the Black Box: A systematic review on explainable artificial intelligence in remote sensing.
IEEE Geoscience and Remote Sensing Magazine 12.4 (Dec. 2024). DOI
Abstract
In recent years, black-box machine learning approaches have become a dominant modeling paradigm for knowledge extraction in remote sensing. Despite the potential benefits of uncovering the inner workings of these models with explainable AI, a comprehensive overview summarizing the explainable AI methods used and their objectives, findings, and challenges in remote sensing applications is still missing. In this paper, we address this gap by performing a systematic review to identify the key trends in the field and shed light on novel explainable AI approaches and emerging directions that tackle specific remote sensing challenges. We also reveal the common patterns of explanation interpretation, discuss the extracted scientific insights, and reflect on the approaches used for the evaluation of explainable AI methods. As such, our review provides a complete summary of the state-of-the-art of explainable AI in remote sensing. Further, we give a detailed outlook on the challenges and promising research directions, representing a basis for novel methodological development and a useful starting point for new researchers in the field.
MCML Authors
The paper introduces EgoCVR, a new benchmark for Composed Video retrieval, where a video and a text description modifying the video content are used to retrieve the relevant video. The study shows that existing methods struggle with this task, and proposes a training-free approach with a re-ranking framework.
EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval.
ECCV 2024 - 18th European Conference on Computer Vision. Milano, Italy, Sep 29-Oct 04, 2024. DOI GitHub
Abstract
In Composed Video Retrieval, a video and a textual description which modifies the video content are provided as inputs to the model. The aim is to retrieve the relevant video with the modified content from a database of videos. In this challenging task, the first step is to acquire large-scale training datasets and collect high-quality benchmarks for evaluation. In this work, we introduce EgoCVR, a new evaluation benchmark for fine-grained Composed Video Retrieval using large-scale egocentric video datasets. EgoCVR consists of 2,295 queries that specifically focus on high-quality temporal video understanding. We find that existing Composed Video Retrieval frameworks do not achieve the necessary high-quality temporal video understanding for this task. To address this shortcoming, we adapt a simple training-free method, propose a generic re-ranking framework for Composed Video Retrieval, and demonstrate that this achieves strong results on EgoCVR.
MCML Authors
Shyamgopal Karthik
Interpretable and Reliable Machine Learning
Iuliana Georgescu
Dr.
Interpretable and Reliable Machine Learning
The work explores how resource efficiency can be integrated into Automated Machine Learning (AutoML), which traditionally focuses on maximizing predictive quality without considering factors like running time or energy consumption.
MetaQuRe: Meta-learning from Model Quality and Resource Consumption.
ECML-PKDD 2024 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Vilnius, Lithuania, Sep 09-13, 2024. DOI
Abstract
Automated machine learning (AutoML) allows for selecting, parametrizing, and composing learning algorithms for a given data set. While resources play a pivotal role in neural architecture search, it is less pronounced by classical AutoML approaches. In fact, they generally focus on only maximizing predictive quality and disregard the importance of finding resource-efficient solutions. To push resource awareness further, our work explicitly explores how measures such as running time or energy consumption can be better considered in AutoML. Firstly, we propose a novel method for algorithm selection that balances multiple performance aspects (including resource demand) as prioritized by the user with the help of compositional meta-learning. Secondly, to foster research on green meta-learning and AutoML, we release the MetaQuRe data set, which contains information on predictive (Qu)ality and (Re)source consumption of models evaluated across hundreds of data sets and four execution environments. We use this data to put our methodology into practice and conduct an in-depth analysis of how our approach and data set can help in making AutoML more resource-aware, which represents our third contribution. Lastly, we publish MetaQuRe alongside an extensive code base, allowing for reproducing all results, expanding our data with results from custom environments, and exploring MetaQuRe interactively. In short, our work demonstrates both the importance as well as benefits of rethinking AutoML and meta-learning in a resource-aware way, thus paving the path for making future ML solutions more sustainable.
MCML Authors
The work introduces GNNavi, a novel prompt-based parameter-efficient fine-tuning (PEFT) approach for Large Language Models (LLMs). The approach addresses the high resource demands of traditional fine-tuning by leveraging Graph Neural Networks (GNNs) to efficiently guide the flow of information during prompt processing.
GNNAVI: Navigating the Information Flow in Large Language Models by Graph Neural Network.
ACL 2024 - Findings of the 62nd Annual Meeting of the Association for Computational Linguistics. Bangkok, Thailand, Aug 11-16, 2024. DOI
Abstract
Large Language Models (LLMs) exhibit strong In-Context Learning (ICL) capabilities when prompts with demonstrations are applied to them. However, fine-tuning still remains crucial to further enhance their adaptability. Prompt-based fine-tuning proves to be an effective fine-tuning method in low-data scenarios, but high demands on computing resources limit its practicality. We address this issue by introducing a prompt-based parameter-efficient fine-tuning (PEFT) approach. GNNavi leverages insights into ICL’s information flow dynamics, which indicates that label words act in prompts as anchors for information propagation. GNNavi employs a Graph Neural Network (GNN) layer to precisely guide the aggregation and distribution of information flow during the processing of prompts by hardwiring the desired information flow into the GNN. Our experiments on text classification tasks with GPT-2 and Llama2 shows GNNavi surpasses standard prompt-based fine-tuning methods in few-shot settings by updating just 0.2% to 0.5% of parameters. We compare GNNavi with prevalent PEFT approaches, such as prefix tuning, LoRA and Adapter in terms of performance and efficiency. Our analysis reveals that GNNavi enhances information flow and ensures a clear aggregation process.
MCML Authors
The work explores parameter-efficient fine-tuning (PEFT) techniques in the context of continual learning and examines the strengths and limitations of rehearsal-free methods, providing valuable insights into how they can be improved for better performance in dynamic, real-world environments.
Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models.
CoLLAs 2024 - 3rd Conference on Lifelong Learning Agents. Pisa, Italy, Aug 11-14, 2024. URL
Abstract
With the advent and recent ubiquity of foundation models, continual learning (CL) has recently shifted from continual training from scratch to the continual adaptation of pretrained models, seeing particular success on rehearsal-free CL benchmarks (RFCL). To achieve this, most proposed methods adapt and restructure parameter-efficient finetuning techniques (PEFT) to suit the continual nature of the problem. Based most often on input-conditional query-mechanisms or regularizations on top of prompt- or adapter-based PEFT, these PEFT-style RFCL (P-RFCL) approaches report peak performances; often convincingly outperforming existing CL techniques. However, on the other end, critical studies have recently highlighted competitive results by training on just the first task or via simple non-parametric baselines. Consequently, questions arise about the relationship between methodological choices in P-RFCL and their reported high benchmark scores. In this work, we tackle these questions to better understand the true drivers behind strong P-RFCL performances, their placement w.r.t. recent first-task adaptation studies, and their relation to preceding CL standards such as EWC or SI. In particular, we show: (1) P-RFCL techniques relying on input-conditional query mechanisms work not because, but rather despite them by collapsing towards standard PEFT shortcut solutions. (2) Indeed, we show how most often, P-RFCL techniques can be matched by a simple and lightweight PEFT baseline. (3) Using this baseline, we identify the implicit bound on tunable parameters when deriving RFCL approaches from PEFT methods as a potential denominator behind P-RFCL efficacy. Finally, we (4) better disentangle continual versus first-task adaptation, and (5) motivate standard RFCL techniques s.a. EWC or SI in light of recent P-RFCL methods.
MCML Authors
The paper explores counterfactual explanations, which help users understand algorithmic decisions by identifying changes that would lead to a desired outcome. These explanations enhance transparency, guide user actions, and provide grounds for contesting decisions.
CountARFactuals – Generating plausible model-agnostic counterfactual explanations with adversarial random forests.
xAI 2024 - 2nd World Conference on Explainable Artificial Intelligence. Valletta, Malta, Jul 17-19, 2024. DOI
Abstract
Counterfactual explanations elucidate algorithmic decisions by pointing to scenarios that would have led to an alternative, desired outcome. Giving insight into the model’s behavior, they hint users towards possible actions and give grounds for contesting decisions. As a crucial factor in achieving these goals, counterfactuals must be plausible, i.e., describing realistic alternative scenarios within the data manifold. This paper leverages a recently developed generative modeling technique – adversarial random forests (ARFs) – to efficiently generate plausible counterfactuals in a model-agnostic way. ARFs can serve as a plausibility measure or directly generate counterfactual explanations. Our ARF-based approach surpasses the limitations of existing methods that aim to generate plausible counterfactual explanations: It is easy to train and computationally highly efficient, handles continuous and categorical data naturally, and allows integrating additional desiderata such as sparsity in a straightforward manner.
MCML Authors
Susanne Dandl
Dr.
* Former Member
Bernd Bischl
Prof. Dr.
Statistical Learning and Data Science
The paper explores feature importance (FI) methods as a means to understand the data-generating process (DGP) in machine learning models, which are often opaque. It provides a comprehensive review of FI methods, new theoretical insights, and practical recommendations for selecting the right approach. The study also discusses uncertainty estimation in FI and future directions for statistical inference from black-box models.
A Guide to Feature Importance Methods for Scientific Inference.
xAI 2024 - 2nd World Conference on Explainable Artificial Intelligence. Valletta, Malta, Jul 17-19, 2024. DOI
Abstract
While machine learning (ML) models are increasingly used due to their high predictive power, their use in understanding the data-generating process (DGP) is limited. Understanding the DGP requires insights into feature-target associations, which many ML models cannot directly provide due to their opaque internal mechanisms. Feature importance (FI) methods provide useful insights into the DGP under certain conditions. Since the results of different FI methods have different interpretations, selecting the correct FI method for a concrete use case is crucial and still requires expert knowledge. This paper serves as a comprehensive guide to help understand the different interpretations of global FI methods. Through an extensive review of FI methods and providing new proofs regarding their interpretation, we facilitate a thorough understanding of these methods and formulate concrete recommendations for scientific inference. We conclude by discussing options for FI uncertainty estimation and point to directions for future research aiming at full statistical inference from black-box ML models.
MCML Authors
Fiona Ewald
Statistical Learning and Data Science
Ludwig Bothmann
Dr.
Statistical Learning and Data Science
Bernd Bischl
Prof. Dr.
Statistical Learning and Data Science
Giuseppe Casalicchio
Dr.
Statistical Learning and Data Science
The paper introduces ETHER, a new approach to parameter-efficient fine-tuning (PEFT), which aims to optimize the adaptation of foundation models to downstream tasks while maintaining generalization ability and minimizing the introduction of extra parameters and computational overhead.
ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections.
ICML 2024 - 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL GitHub
Abstract
Parameter-efficient finetuning (PEFT) has become ubiquitous to adapt foundation models to downstream task requirements while retaining their generalization ability. However, the amount of additionally introduced parameters and compute for successful adaptation and hyperparameter searches can explode quickly, especially when deployed at scale to serve numerous individual requests. To ensure effective, parameter-efficient, and hyperparameter-robust adaptation, we propose the ETHER transformation family, which performs Efficient fineTuning via HypErplane Reflections. By design, ETHER transformations require a minimal number of parameters, are less likely to deteriorate model performance, and exhibit robustness to hyperparameter and learning rate choices. In particular, we introduce ETHER and its relaxation ETHER+, which match or outperform existing PEFT methods with significantly fewer parameters (∼10-100 times lower than LoRA or OFT) across multiple image synthesis and natural language tasks without exhaustive hyperparameter tuning. Finally, we investigate the recent emphasis on Hyperspherical Energy retention for adaptation and raise questions on its practical utility.
MCML Authors
The position paper critiques the current focus on high predictive accuracy in deep learning, particularly for supervised tasks involving large image and language datasets, and calls for greater attention to overlooked metrics and data types, such as uncertainty, active learning, continual learning, and scientific data.
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI.
ICML 2024 - 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
Abstract
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential.
MCML Authors
David Rügamer
Prof. Dr.
Statistics, Data Science and Machine Learning
The paper explores a new method for learning structured representations by leveraging quadratic optimal transport, enhancing the interpretability of learned features.
Disentangled Representation Learning through Geometry Preservation with the Gromov-Monge Gap.
SPIGM @ICML 2024 - Workshop on Structured Probabilistic Inference & Generative Modeling at the 41st International Conference on Machine Learning (ICML 2024). Vienna, Austria, Jul 21-27, 2024. arXiv
Abstract
Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning. Solving it may unlock other problems, such as generalization, interpretability, or fairness. Although remarkably challenging to solve in theory, disentanglement is often achieved in practice through prior matching. Furthermore, recent works have shown that prior matching approaches can be enhanced by leveraging geometrical considerations, e.g., by learning representations that preserve geometric features of the data, such as distances or angles between points. However, matching the prior while preserving geometric features is challenging, as a mapping that fully preserves these features while aligning the data distribution with the prior does not exist in general. To address these challenges, we introduce a novel approach to disentangled representation learning based on quadratic optimal transport. We formulate the problem using Gromov-Monge maps that transport one distribution onto another with minimal distortion of predefined geometric features, preserving them as much as can be achieved. To compute such maps, we propose the Gromov-Monge-Gap (GMG), a regularizer quantifying whether a map moves a reference distribution with minimal geometry distortion. We demonstrate the effectiveness of our approach for disentanglement across four standard benchmarks, outperforming other methods leveraging geometric considerations.
MCML Authors
The study introduces Divergent Token Metrics as a novel method for evaluating compressed large language models (LLMs), offering a deeper analysis of model degradation during compression, and providing a more effective way to optimize these models beyond traditional metrics like perplexity and accuracy.
Divergent Token Metrics: Measuring degradation to prune away LLM components -- and optimize quantization.
NAACL 2024 - Annual Conference of the North American Chapter of the Association for Computational Linguistics. Mexico City, Mexico, Jun 16-21, 2024. DOI
Abstract
Large Language Models (LLMs) have reshaped natural language processing with their impressive capabilities. However, their ever-increasing size has raised concerns about their effective deployment and the need for LLM compression. This study introduces the Divergent Token Metrics (DTMs), a novel approach to assessing compressed LLMs, addressing the limitations of traditional perplexity or accuracy measures that fail to accurately reflect text generation quality. DTMs measure token divergences that allow deeper insights into the subtleties of model compression, in particular, when evaluating components’ impacts individually. Utilizing the First Divergent Token Metric (FDTM) in model sparsification reveals that 25% of all attention components can be pruned beyond 90% on the Llama-2 model family, still keeping SOTA performance. For quantization, FDTM suggests that more than 80% of parameters can be naively transformed to int8 without special outlier management. These evaluations indicate the necessity of choosing appropriate compressions for parameters individually—and that FDTM can identify those—while standard metrics result in deteriorated outcomes.
MCML Authors
Matthias Aßenmacher
Dr.
Statistical Learning and Data Science
The paper improves Optimal Transport (OT), a method for efficiently transforming one set of data into another. The new UOT-FM approach helps in areas like predicting biological changes and improving image processing by making the transformation more flexible and accurate. This makes OT more useful for real-world applications.
Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation.
ICLR 2024 - 12th International Conference on Learning Representations. Vienna, Austria, May 07-11, 2024. URL
Abstract
In optimal transport (OT), a Monge map is known as a mapping that transports a source distribution to a target distribution in the most cost-efficient way. Recently, multiple neural estimators for Monge maps have been developed and applied in diverse unpaired domain translation tasks, e.g. in single-cell biology and computer vision. However, the classic OT framework enforces mass conservation, which makes it prone to outliers and limits its applicability in real-world scenarios. The latter can be particularly harmful in OT domain translation tasks, where the relative position of a sample within a distribution is explicitly taken into account. While unbalanced OT tackles this challenge in the discrete setting, its integration into neural Monge map estimators has received limited attention. We propose a theoretically grounded method to incorporate unbalancedness into any Monge map estimator. We improve existing estimators to model cell trajectories over time and to predict cellular responses to perturbations. Moreover, our approach seamlessly integrates with the OT flow matching (OT-FM) framework. While we show that OT-FM performs competitively in image translation, we further improve performance by incorporating unbalancedness (UOT-FM), which better preserves relevant features. We hence establish UOT-FM as a principled method for unpaired image translation.
MCML Authors
The work explores the ethical challenges in the algorithmization of concepts like fairness and diversity in AI. The authors advocate for caution when algorithmically implementing ethical principles and emphasize the importance of human oversight to ensure these systems do not mislead or oversimplify complex ethical dilemmas.
Is diverse and inclusive AI trapped in the gap between reality and algorithmizability?
NLDL 2024 - Northern Lights Deep Learning Conference. Tromsø, Norway, Jan 09-11, 2024. URL
Abstract
We investigate the preconditions of an operationalization of ethics on the example algorithmization, i.e. the mathematical implementation, of the concepts of fairness and diversity in AI. From a non-technical point of view in ethics, this implementation entails two major drawbacks, (1) as it narrows down big concepts to a single model that is deemed manageable, and (2) as it hides unsolved problems of humanity in a system that could be mistaken as the `solution’ to these problems. We encourage extra caution when dealing with such issues and vote for human oversight.
MCML Authors
The work introduces a way to create new test functions for optimization problems, where specific characteristics of the problem landscape can be chosen in advance. By adjusting random data and training a simple neural network, the method can recreate known test functions and also generate new ones with properties not seen before.
Neural Networks as Black-Box Benchmark Functions Optimized for Exploratory Landscape Features.
FOGA 2023 - 17th ACM/SIGEVO Conference on Foundations of Genetic Algorithms. Potsdam, Germany, Aug 30-Sep 01, 2023. DOI
Abstract
Artificial benchmark functions are commonly used in optimization research because of their ability to rapidly evaluate potential solutions, making them a preferred substitute for real-world problems. However, these benchmark functions have faced criticism for their limited resemblance to real-world problems. In response, recent research has focused on automatically generating new benchmark functions for areas where established test suites are inadequate. These approaches have limitations, such as the difficulty of generating new benchmark functions that exhibit exploratory landscape analysis (ELA) features beyond those of existing benchmarks. The objective of this work is to develop a method for generating benchmark functions for single-objective continuous optimization with user-specified structural properties. Specifically, we aim to demonstrate a proof of concept for a method that uses an ELA feature vector to specify these properties in advance. To achieve this, we begin by generating a random sample of decision space variables and objective values. We then adjust the objective values using CMA-ES until the corresponding features of our new problem match the predefined ELA features within a specified threshold. By iteratively transforming the landscape in this way, we ensure that the resulting function exhibits the desired properties. To create the final function, we use the resulting point cloud as training data for a simple neural network that produces a function exhibiting the target ELA features. We demonstrate the effectiveness of this approach by replicating the existing functions of the well-known BBOB suite and creating new functions with ELA feature values that are not present in BBOB.
MCML Authors
Lennart Schneider
Statistical Learning and Data Science
Bernd Bischl
Prof. Dr.
Statistical Learning and Data Science
The paper presents the mlr3fairness package which builds upon the ML framework mlr3. The extension contains fairness metrics, fairness visualizations, and model-agnostic pre- and post-processing operators that aim to reduce biases in ML models.
Fairness Audits and Debiasing Using mlr3fairness.
The R Journal 15.1 (Aug. 2023). DOI
Abstract
Given an increase in data-driven automated decision-making based on machine learning (ML) models, it is imperative that, along with tools to develop and improve such models, there are sufficient capabilities to analyze and assess models with respect to potential biases. We present the package mlr3fairness, a collection of metrics and methods that allow for the assessment of bias in machine learning models. Our package implements a variety of widely used fairness metrics that can be used to audit models for potential biases, along with a set of visualizations that can help to provide additional insights into such biases. mlr3fairness furthermore integrates bias mitigation methods for machine learning models through data pre-processing or post-processing of predictions. These allow practitioners to trade off performance and fairness metrics that are appropriate for their use case.
MCML Authors
Florian Pfisterer
Dr.
* Former Member
Bernd Bischl
Prof. Dr.
Statistical Learning and Data Science
The paper investigates whether pre-trained multilingual language models (PMLMs) impose English moral norms on other languages or show random, potentially harmful biases. Experiments in five languages reveal that the models do encode different moral biases, but these do not consistently reflect real cultural differences. This could cause problems when using such models across languages.
Speaking Multiple Languages Affects the Moral Bias of Language Models.
ACL 2023 - Findings of the 61th Annual Meeting of the Association for Computational Linguistics. Toronto, Canada, Jul 09-14, 2023. DOI
Abstract
Pre-trained multilingual language models (PMLMs) are commonly used when dealing with data from multiple languages and cross-lingual transfer. However, PMLMs are trained on varying amounts of data for each language. In practice this means their performance is often much better on English than many other languages. We explore to what extent this also applies to moral norms. Do the models capture moral norms from English and impose them on other languages? Do the models exhibit random and thus potentially harmful beliefs in certain languages? Both these issues could negatively impact cross-lingual transfer and potentially lead to harmful outcomes. In this paper, we (1) apply the MORALDIRECTION framework to multilingual models, comparing results in German, Czech, Arabic, Chinese, and English, (2) analyse model behaviour on filtered parallel subtitles corpora, and (3) apply the models to a Moral Foundations Questionnaire, comparing with human responses from different countries. Our experiments demonstrate that, indeed, PMLMs encode differing moral biases, but these do not necessarily correspond to cultural differences or commonalities in human opinions. We release our code and models.
MCML Authors
Katharina Hämmerl
Data Analytics & Statistics
