Probing Association Biases in LLM Moderation Over-Sensitivity

Large Language Models are widely used for content moderation but often misclassify benign comments as toxic, leading to over-sensitivity. While previous research attributes this issue primarily to the presence of offensive terms, we reveal a potential cause beyond token level: LLMs exhibit systematic topic biases in their implicit associations. Inspired by cognitive psychology's implicit association tests, we introduce Topic Association Analysis, a semantic-level approach to quantify how LLMs associate certain topics with toxicity. By prompting LLMs to generate free-form scenario imagination for misclassified benign comments and analyzing their topic amplification levels, we find that more advanced models (e.g., GPT-4 Turbo) demonstrate stronger topic stereotype despite lower overall false positive rates. These biases suggest that LLMs do not merely react to explicit, offensive language but rely on learned topic associations, shaping their moderation decisions. Our findings highlight the need for refinement beyond keyword-based filtering, providing insights into the underlying mechanisms driving LLM over-sensitivity.

Translation in the Wild

Large Language Models (LLMs) excel in translation among other things, demonstrating competitive performance for many language pairs in zero- and few-shot settings. But unlike dedicated neural machine translation models, LLMs are not trained on any translation-related objective. What explains their remarkable translation abilities? Are these abilities grounded in "incidental bilingualism" (Briakou et al. 2023) in training data? Does instruction tuning contribute to it? Are LLMs capable of aligning and leveraging semantically identical or similar monolingual contents from different corners of the internet that are unlikely to fit in a single context window? I offer some reflections on this topic, informed by recent studies and growing user experience. My working hypothesis is that LLMs' translation abilities originate in two different types of pre-training data that may be internalized by the models in different ways. I discuss the prospects for testing the "duality" hypothesis empirically and its implications for reconceptualizing translation, human and machine, in the age of deep learning.

Tell, Don't Show: Leveraging Language Models' Abstractive Retellings to Model Literary Themes

Conventional bag-of-words approaches for topic modeling, like latent Dirichlet allocation (LDA), struggle with literary text. Literature challenges lexical methods because narrative language focuses on immersive sensory details instead of abstractive description or exposition: writers are advised to "show, don't tell." We propose Retell, a simple, accessible topic modeling approach for literature. Here, we prompt resource-efficient, generative language models (LMs) to tell what passages show, thereby translating narratives' surface forms into higher-level concepts and themes. By running LDA on LMs' retellings of passages, we can obtain more precise and informative topics than by running LDA alone or by directly asking LMs to list topics. To investigate the potential of our method for cultural analytics, we compare our method's outputs to expert-guided annotations in a case study on racial/cultural identity in high school English language arts books.

Improving Multilingual Social Media Insights: Aspect-based Comment Analysis

The inherent nature of social media posts, characterized by the freedom of language use with a disjointed array of diverse opinions and topics, poses significant challenges to downstream NLP tasks such as comment clustering, comment summarization, and social media opinion analysis. To address this, we propose a granular level of identifying and generating aspect terms from individual comments to guide model attention. Specifically, we leverage multilingual large language models with supervised fine-tuning for comment aspect term generation (CAT-G), further aligning the model's predictions with human expectations through DPO. We demonstrate the effectiveness of our method in enhancing the comprehension of social media discourse on two NLP tasks. Moreover, this paper contributes the first multilingual CAT-G test set on English, Chinese, Malay, and Bahasa Indonesian. As LLM capabilities vary among languages, this test set allows for a comparative analysis of performance across languages with varying levels of LLM proficiency.

LLMs for Argument Mining: Detection, Extraction, and Relationship Classification of pre-defined Arguments in Online Comments

Automated large-scale analysis of public discussions around contested issues like abortion requires detecting and understanding the use of arguments. While Large Language Models (LLMs) have shown promise in language processing tasks, their performance in mining topic-specific, pre-defined arguments in online comments remains underexplored. We evaluate four state-of-the-art LLMs on three argument mining tasks using datasets comprising over 2,000 opinion comments across six polarizing topics. Quantitative evaluation suggests an overall strong performance across the three tasks, especially for large and fine-tuned LLMs, albeit at a significant environmental cost. However, a detailed error analysis revealed systematic shortcomings on long and nuanced comments and emotionally charged language, raising concerns for downstream applications like content moderation or opinion analysis. Our results highlight both the promise and current limitations of LLMs for automated argument analysis in online comments.

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning

Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approaches rely heavily on formal proof systems that poorly align with LLMs' strength derived from informal, natural language knowledge acquired during pre-training. In this work, we propose DeepTheorem, a comprehensive informal theorem-proving framework exploiting natural language to enhance LLM mathematical reasoning. DeepTheorem includes a large-scale benchmark dataset consisting of 121K high-quality IMO-level informal theorems and proofs spanning diverse mathematical domains, rigorously annotated for correctness, difficulty, and topic categories, accompanied by systematically constructed verifiable theorem variants. We devise a novel reinforcement learning strategy (RL-Zero) explicitly tailored to informal theorem proving, leveraging the verified theorem variants to incentivize robust mathematical inference. Additionally, we propose comprehensive outcome and process evaluation metrics examining proof correctness and the quality of reasoning steps. Extensive experimental analyses demonstrate DeepTheorem significantly improves LLM theorem-proving performance compared to existing datasets and supervised fine-tuning protocols, achieving state-of-the-art accuracy and reasoning quality. Our findings highlight DeepTheorem's potential to fundamentally advance automated informal theorem proving and mathematical exploration.

From Chat Logs to Collective Insights: Aggregative Question Answering

Conversational agents powered by large language models (LLMs) are rapidly becoming integral to our daily interactions, generating unprecedented amounts of conversational data. Such datasets offer a powerful lens into societal interests, trending topics, and collective concerns. Yet, existing approaches typically treat these interactions as independent and miss critical insights that could emerge from aggregating and reasoning across large-scale conversation logs. In this paper, we introduce Aggregative Question Answering, a novel task requiring models to reason explicitly over thousands of user-chatbot interactions to answer aggregative queries, such as identifying emerging concerns among specific demographics. To enable research in this direction, we construct a benchmark, WildChat-AQA, comprising 6,027 aggregative questions derived from 182,330 real-world chatbot conversations. Experiments show that existing methods either struggle to reason effectively or incur prohibitive computational costs, underscoring the need for new approaches capable of extracting collective insights from large-scale conversational data.

Can Large Language Models Match the Conclusions of Systematic Reviews?

Systematic reviews (SR), in which experts summarize and analyze evidence across individual studies to provide insights on a specialized topic, are a cornerstone for evidence-based clinical decision-making, research, and policy. Given the exponential growth of scientific articles, there is growing interest in using large language models (LLMs) to automate SR generation. However, the ability of LLMs to critically assess evidence and reason across multiple documents to provide recommendations at the same proficiency as domain experts remains poorly characterized. We therefore ask: Can LLMs match the conclusions of systematic reviews written by clinical experts when given access to the same studies? To explore this question, we present MedEvidence, a benchmark pairing findings from 100 SRs with the studies they are based on. We benchmark 24 LLMs on MedEvidence, including reasoning, non-reasoning, medical specialist, and models across varying sizes (from 7B-700B). Through our systematic evaluation, we find that reasoning does not necessarily improve performance, larger models do not consistently yield greater gains, and knowledge-based fine-tuning degrades accuracy on MedEvidence. Instead, most models exhibit similar behavior: performance tends to degrade as token length increases, their responses show overconfidence, and, contrary to human experts, all models show a lack of scientific skepticism toward low-quality findings. These results suggest that more work is still required before LLMs can reliably match the observations from expert-conducted SRs, even though these systems are already deployed and being used by clinicians. We release our codebase and benchmark to the broader research community to further investigate LLM-based SR systems.

AI Mathematician: Towards Fully Automated Frontier Mathematical Research

Large Reasoning Models (LRMs) have made significant progress in mathematical capabilities in recent times. However, these successes have been primarily confined to competition-level problems. In this work, we propose AI Mathematician (AIM) framework, which harnesses the reasoning strength of LRMs to support frontier mathematical research. We have identified two critical challenges of mathematical research compared to competition, {\it the intrinsic complexity of research problems} and {\it the requirement of procedural rigor}. To address these challenges, AIM incorporates two core strategies: an exploration mechanism to foster longer solution paths, and the pessimistic reasonable verification method to ensure reliability. This early version of AIM already exhibits strong capability in tackling research-level tasks. We conducted extensive experiments across several real-world mathematical topics and obtained promising results. AIM is able to autonomously construct substantial portions of proofs and uncover non-trivial insights within each research area. These findings highlight the potential of LRMs in mathematical discovery and suggest that LRM-based agent systems could significantly accelerate mathematical research in the future.

Arbiters of Ambivalence: Challenges of Using LLMs in No-Consensus Tasks

The increasing use of LLMs as substitutes for humans in ``aligning'' LLMs has raised questions about their ability to replicate human judgments and preferences, especially in ambivalent scenarios where humans disagree. This study examines the biases and limitations of LLMs in three roles: answer generator, judge, and debater. These roles loosely correspond to previously described alignment frameworks: preference alignment (judge) and scalable oversight (debater), with the answer generator reflecting the typical setting with user interactions. We develop a ``no-consensus'' benchmark by curating examples that encompass a variety of a priori ambivalent scenarios, each presenting two possible stances. Our results show that while LLMs can provide nuanced assessments when generating open-ended answers, they tend to take a stance on no-consensus topics when employed as judges or debaters. These findings underscore the necessity for more sophisticated methods for aligning LLMs without human oversight, highlighting that LLMs cannot fully capture human disagreement even on topics where humans themselves are divided.