Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 08497v1 Announce Type: new Abstract: As deep language models (DLMs) are increasingly deployed in high-stakes domains such as healthcare, understanding their decision rationale becomes paramount for ensuring trust, safety, and accountability.
arXiv:2606. 08841v1 Announce Type: new Abstract: Text-to-image diffusion models are increasingly deployed in open-ended creative contexts, yet their outputs remain impersonal, optimized for aggregate aesthetics rather than individual taste.
arXiv:2606. 07544v1 Announce Type: cross Abstract: Middle school is a key window for building core academic skills and the learning routines students carry into later grades, yet many students still fall behind because help is often limited and comes too late, after they have already been stuck for a while.
arXiv:2606. 07552v1 Announce Type: cross Abstract: Large language models exhibit innate behavioral tendencies when deployed as strategic agents -- notably a risk-averse "turtle" bias toward defensive play.
arXiv:2606. 07608v1 Announce Type: cross Abstract: We present a systematic study of fine-tuning OpenAI's Whisper large-v3 for Swiss German ASR, using 1,367 hours of broadcast speech paired with Standard German subtitles as weak supervision.
arXiv:2606. 07604v1 Announce Type: cross Abstract: Analyzing attention weights has become a standard approach for interpreting the information flow of Large Language Models (LLMs).
arXiv:2606. 07612v1 Announce Type: cross Abstract: We argue that many Anthropomorphic Misalignment Research (AMR) studies need stronger evidence to ensure that they can provide a robust foundation for critical safety decisions, such as model deployment and regulation.
arXiv:2606. 07696v1 Announce Type: cross Abstract: Activation steering has become a popular training-free method to control LLM behavior by injecting precomputed direction vectors into the model's residual stream at inference time.
arXiv:2606. 07705v1 Announce Type: cross Abstract: Although multi-objective reinforcement learning (MORL) is central to aligning large language models with complex human preferences, the prevailing practice of static weighted summation overlooks a more fundamental phenomenon: reward learning is markedly asynchronous across objectives.
arXiv:2606. 07706v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge.
arXiv:2606. 07924v1 Announce Type: cross Abstract: This paper presents our system description for the 2nd Workshop on Multimodal Augmented Generation via MultimodAl Retrieval (MAGMaR).
arXiv:2606. 07951v1 Announce Type: cross Abstract: Humans increasingly turn to Language Models (LMs) in ways that shape beliefs and drive decisions, including discussing, rewriting, and summarizing information from scientific articles, news, and medical reports.
arXiv:2606. 07968v1 Announce Type: cross Abstract: Reasoning-capable large language models can be induced to spend their generation budget on injected decoy tasks rather than answering the user's question, causing denial of service when no final answer is produced and denial of wallet when excess output tokens are billed.
arXiv:2606. 07996v1 Announce Type: cross Abstract: Pretraining is fundamental to the development of Large Language Models (LLMs), yet the opacity of pretraining data complicates model analysis and raises ethical, legal, and fairness concerns.
arXiv:2604. 26498v3 Announce Type: replace Abstract: The rapid growth of molecular foundation models and large language models (LLMs) has encouraged a scale centred view of AI in drug discovery, in which larger pretrained models are expected to supersede compact cheminformatics models.
arXiv:2605. 03357v2 Announce Type: replace Abstract: Mean Field Games (MFGs) provide a powerful framework for modeling the collective behavior of large populations of interacting agents.
arXiv:2606. 08081v1 Announce Type: cross Abstract: Repeated reference games test whether interlocutors replace their initially long descriptions with shorter, partner-specific conventions grounded in shared interaction history.
arXiv:2606. 08172v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly mediate high-stakes interactions in finance, medicine, and mental-health support, yet users have limited control over how these systems communicate.
arXiv:2606. 08131v1 Announce Type: cross Abstract: Conversational AI is increasingly used for advice, interpretation, reassurance, and decision support in contexts where users may be vulnerable, uncertain, or dependent on the system's apparent competence.
arXiv:2606. 08602v1 Announce Type: cross Abstract: We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems.