arXiv:2604.02669v1 Announce Type: new Abstract: How biased is a language model? The answer depends on how you ask. A model that refuses to choose between castes for a leadership role will, in a fill-in-the-blank task, reliably associate upper castes with purity and lower castes with lack of hygiene.
arXiv:2604.02668v1 Announce Type: new Abstract: Large language models (LLMs) often exhibit sycophancy: agreement with user stance even when it conflicts with the model's opinion. While prior work has mostly studied this in single-agent settings, it remains underexplored in collaborative multi-agent
arXiv:2604.02660v1 Announce Type: new Abstract: As Large Language Models (LLMs) increasingly power decision-making systems across critical domains, understanding and mitigating their biases becomes essential for responsible AI deployment. Although bias assessment frameworks have proliferated for att
arXiv:2604.02650v1 Announce Type: new Abstract: Existing studies on Long-Context Continual Pre-training (LCCP) mainly focus on small-scale models and limited data regimes (tens of billions of tokens). We argue that directly migrating these small-scale settings to industrial-grade models risks insuff
arXiv:2604.02645v1 Announce Type: new Abstract: This work aims to shine a spotlight on the topic of metalanguage. We first define metalanguage, link it to NLP and LLMs, and then discuss our two labs' metalanguage-centered efforts. Finally, we discuss four dimensions of metalanguage and metalinguisti
arXiv:2604.02640v1 Announce Type: new Abstract: Performance evaluation of Retrieval-Augmented Generation (RAG) systems within enterprise environments is governed by multi-dimensional and composite factors extending far beyond simple final accuracy checks. These factors include reasoning complexity,
arXiv:2604.02637v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly persuasive, there is concern that people's opinions and decisions may be influenced across various contexts at scale. Prior mitigation (e.g., AI detectors and disclaimers) largely treats people as pas
arXiv:2604.02621v1 Announce Type: new Abstract: Reinforcement Learning (RL) has been shown to substantially improve the reasoning capability of small and large language models (LLMs), but existing approaches typically rely on verifiable rewards, hence ground truth labels. We propose an RL framework
arXiv:2604.02596v1 Announce Type: new Abstract: In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks from a few examples, making it promising for languages underrepresented in pre-training. Recent work on many-shot ICL suggests that modern LLMs can further benefit from
arXiv:2604.02560v1 Announce Type: new Abstract: Discrete diffusion language models (dLLMs) accelerate text generation by unmasking multiple tokens in parallel. However, parallel decoding introduces a distributional mismatch: it approximates the joint conditional using a fully factorized product of p
arXiv:2604.02557v1 Announce Type: new Abstract: Language models are known to exhibit various forms of cultural bias in decision-making tasks, yet much less is known about their degree of cultural familiarity in open-ended text generation tasks. In this paper, we introduce the task of culturally-adap
arXiv:2604.02554v1 Announce Type: new Abstract: Diversity-aware retrieval is essential for Retrieval-Augmented Generation (RAG), yet existing methods lack theoretical guarantees and face scalability issues as the number of retrieved passages $k$ increases. We propose a principled formulation of dive
arXiv:2604.02537v1 Announce Type: new Abstract: All-atom molecular dynamics (MD) simulations can predict polymer properties from molecular structure, yet their execution requires specialized expertise in force field selection, system construction, equilibration, and property extraction. We present P
arXiv:2604.02512v1 Announce Type: new Abstract: Large language models (LLMs) increasingly exhibit human-like patterns of pragmatic and social reasoning. This paper addresses two related questions: do LLMs approximate human social meaning not only qualitatively but also quantitatively, and can prompt
arXiv:2604.02485v1 Announce Type: new Abstract: Confirmation bias, the tendency to seek evidence that supports rather than challenges one's belief, hinders one's reasoning ability. We examine whether large language models (LLMs) exhibit confirmation bias by adapting the rule-discovery study from hum
arXiv:2604.02460v1 Announce Type: new Abstract: Recent work reports strong performance from multi-agent LLM systems (MAS), but these gains are often confounded by increased test-time computation. When computation is normalized, single-agent systems (SAS) can match or outperform MAS, yet the theoreti
arXiv:2604.02451v1 Announce Type: new Abstract: Modeling coherence in text has been a task that has excited NLP researchers since a long time. It has applications in detecting incoherent structures and helping the author fix them. There has been recent work in using neural networks to extract a skel
arXiv:2604.02423v1 Announce Type: new Abstract: Large language models exhibit sycophancy: the tendency to shift outputs toward user-expressed stances, regardless of correctness or consistency. While prior work has studied this issue and its impacts, rigorous computational linguistic metrics are need
arXiv:2604.02362v1 Announce Type: new Abstract: Decoding speech information from scalp EEG remains difficult due to low SNR and spatial blurring. We present CIPHER (Conformer-based Inference of Phonemes from High-density EEG Representations), a dual-pathway model using (i) ERP features and (ii) broa
arXiv:2604.02359v1 Announce Type: new Abstract: General-purpose Large Language Models (LLMs) are becoming widely adopted by people for mental health support. Yet emerging evidence suggests there are significant risks associated with high-frequency use, particularly for individuals suffering from psy