Research Group Michael Hedderich

Discourse understanding is essential for many NLP tasks, yet most existing work remains constrained by framework-dependent discourse representations. This work investigates whether large language models (LLMs) capture discourse knowledge that generalizes across languages and frameworks. We address this question along two dimensions: (1) developing a unified discourse relation label set to facilitate cross-lingual and cross-framework discourse analysis, and (2) probing LLMs to assess whether they encode generalizable discourse abstractions. Using multilingual discourse relation classification as a testbed, we examine a comprehensive set of 23 LLMs of varying sizes and multilingual capabilities. Our results show that LLMs, especially those with multilingual training corpora, can generalize discourse information across languages and frameworks. Further layer-wise analyses reveal that language generalization at the discourse level is most salient in the intermediate layers. Lastly, our error analysis provides an account of challenging relation classes.

People can generate high-quality ideas by building on each other’s ideas. By enabling individuals to contribute their ideas at their own comfortable time and method (i.e., asynchronous ideation), they can deeply engage in ideation and improve idea quality. However, running asynchronous ideation faces a practical constraint. Whereas trained human facilitators are needed to guide effective idea exchange, they cannot be continuously available to engage with individuals joining at varying hours. In this paper, we ask how chatbots can be designed to facilitate asynchronous ideation. For this, we adopted the guidelines found in the literature about human facilitators and designed two chatbots: one provides a structured ideation process, and another adapts the ideation process to individuals’ ideation performance. We invited 48 participants to generate and select ideas by interacting with one of our chatbots and invited an expert facilitator to review our chatbots. We found that both chatbots can guide users to build on each other’s ideas and converge them into a few satisfying ideas. However, we also found the chatbots’ limitations in social interaction with collaborators, which only human facilitators can provide. Accordingly, we conclude that chatbots can be promising facilitators of asynchronous ideation, but hybrid facilitation with human facilitators would be needed to address the social aspects of collaborative ideation.

Recent advances in Large Language Models (LLMs) have sparked wide interest in validating and comprehending the human-like cognitive-behavioral traits LLMs may capture and convey. These cognitive-behavioral traits include typically Attitudes, Opinions, Values (AOVs). However, measuring AOVs embedded within LLMs remains opaque, and different evaluation methods may yield different results. This has led to a lack of clarity on how different studies are related to each other and how they can be interpreted. This paper aims to bridge this gap by providing a comprehensive overview of recent works on the evaluation of AOVs in LLMs. Moreover, we survey related approaches in different stages of the evaluation pipeline in these works. By doing so, we address the potential and challenges with respect to understanding the model, human-AI alignment, and downstream application in social sciences. Finally, we provide practical insights into evaluation methods, model enhancement, and interdisciplinary collaboration, thereby contributing to the evolving landscape of evaluating AOVs in LLMs.

Traditional benchmarking in NLP typically involves using static held-out test sets. However, this approach often results in an overestimation of performance and lacks the ability to offer comprehensive, interpretable, and dynamic assessments of NLP models. Recently, works like DynaBench (Kiela et al., 2021) and CheckList (Ribeiro et al., 2020) have addressed these limitations through behavioral testing of NLP models with test types generated by a multistep human-annotated pipeline. Unfortunately, manually creating a variety of test types requires much human labor, often at prohibitive cost. In this work, we propose SYNTHEVAL, a hybrid behavioral testing framework that leverages large language models (LLMs) to generate a wide range of test types for a comprehensive evaluation of NLP models. SYNTHEVAL first generates sentences via LLMs using controlled generation, and then identifies challenging examples by comparing the predictions made by LLMs with task-specific NLP models. In the last stage, human experts investigate the challenging examples, manually design templates, and identify the types of failures the taskspecific models consistently exhibit. We apply SYNTHEVAL to two classification tasks, sentiment analysis and toxic language detection, and show that our framework is effective in identifying weaknesses of strong models on these tasks.

Tree of Thoughts (ToT) is a reasoning strategy for Large Language Models (LLMs) that employs a generator to suggest reasoning steps and a discriminator to decide which steps to implement. ToT demonstrates strong performance on reasoning tasks, often surpassing simple methods such as Input-Output (IO) prompting and Chain-of-Thought (CoT) reasoning. However, ToT does not consistently outperform such simpler methods across all models, leaving large knowledge gaps on the conditions under which ToT is most beneficial. In this paper, we analyze the roles of the generator and discriminator separately to better understand the conditions when ToT is beneficial. We find that the generator plays a more critical role than the discriminator in driving the success of ToT. Scaling the generator leads to notable improvements in ToT performance, even when using a smaller model as the discriminator, whereas scaling the discriminator with a fixed generator yields only marginal gains. Our results show that models across different scales exhibit comparable discrimination capabilities, yet differ significantly in their generative performance for ToT.

Topic modeling is a key method in text analysis, but existing approaches are limited by assuming one topic per document or fail to scale efficiently for large, noisy datasets of short texts. We introduce Semantic Component Analysis (SCA), a novel topic modeling technique that overcomes these limitations by discovering multiple, nuanced semantic components beyond a single topic in short texts which we accomplish by introducing a decomposition step to the clustering-based topic modeling framework. Evaluated on multiple Twitter datasets, SCA matches the state-of-the-art method BERTopic in coherence and diversity, while uncovering at least double the semantic components and maintaining a noise rate close to zero while staying scalable and effective across languages, including an underrepresented one.

One barrier to deeper adoption of user-research methods is the amount of labor required to create high-quality representations of collected data. Trained user researchers need to analyze datasets and produce informative summaries pertaining to the original data. While Large Language Models (LLMs) could assist in generating summaries, they are known to hallucinate and produce biased responses. In this paper, we study human–AI workflows that differently delegate subtasks in user research between human experts and LLMs. Studying persona generation as our case, we found that LLMs are not good at capturing key characteristics of user data on their own. Better results are achieved when we leverage human skill in grouping user data by their key characteristics and exploit LLMs for summarizing pre-grouped data into personas. Personas generated via this collaborative approach can be more representative and empathy-evoking than ones generated by human experts or LLMs alone. We also found that LLMs could mimic generated personas and enable interaction with personas, thereby helping user researchers empathize with them. We conclude that LLMs, by facilitating the analysis of user data, may promote widespread application of qualitative methods in user research.