Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608.30372v1 Announce Type: new Abstract: As Large Language Models rapidly advance, performance on standard multiple-choice question answering (MCQA) benchmarks is reaching saturation. While th...
arXiv:2608.30725v1 Announce Type: new Abstract: Recent multilingual vision--language encoders cover hundreds of languages in a single model, yet on two state-of-the-art instances retrieval on low-res...
arXiv:2608.30902v1 Announce Type: new Abstract: Adapting large language models to user-specific preferences is often constrained by the cost of human annotation, making preference optimisation imprac...
arXiv:2608.30924v1 Announce Type: new Abstract: Travel itinerary generation requires balancing strict spatio-temporal constraints with human preferences. Existing LLM-based planners mainly rely on st...
arXiv:2608.30996v1 Announce Type: new Abstract: Retrieval-augmented generation systems can precompute and store key-value caches of retrieved documents to avoid re-encoding context at every query. Qu...
arXiv:2608.31128v1 Announce Type: new Abstract: Large language models (LLMs) offer promising clinical decision support but remain vulnerable to hallucinated facts, unsupported recommendations, and ci...
arXiv:2505.17537v2 Announce Type: replace Abstract: Large language models (LLMs) often produce incorrect answers with high confidence, yet the factors associated with such overconfidence remain insuf...
arXiv:2508.16013v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in politically sensitive contexts, raising concerns about their susceptibility to ideologica...
arXiv:2601.06631v2 Announce Type: replace Abstract: Building NLP systems for subjective tasks requires one to ensure their alignment to contrasting human values. We propose the MultiCalibrated Subjec...
arXiv:2601.16690v2 Announce Type: replace Abstract: We introduce EMemBench, a programmatic benchmark generator for evaluating long-term episodic memory of agents through interactive games. Rather tha...
arXiv:2603.12165v3 Announce Type: replace Abstract: Synthetic data has become essential for training code generation models, yet it introduces significant noise and hallucinations that are difficult...
arXiv:2603.16622v2 Announce Type: replace Abstract: Instead of directly distilling a language model, this study addresses the problem of aligning a base model with a target model in distribution by d...
arXiv:2603.25201v2 Announce Type: replace Abstract: Recent research points toward LLMs being manipulated through adversarial and seemingly benign inputs, resulting in harmful, biased, or policy-viola...
arXiv:2606.03695v2 Announce Type: replace Abstract: As language models are increasingly deployed in real-world applications, the ability to erase specific knowledge from them becomes critical for saf...
arXiv:2606.04483v2 Announce Type: replace Abstract: Existing jailbreaks against aligned LLMs are discrete artifacts whose surface forms are easy to fingerprint and patch. We argue that the broader fa...
arXiv:2606.11167v2 Announce Type: replace Abstract: Full-duplex spoken dialogue models can listen and speak simultaneously, making them a promising architecture for natural conversation. However, cur...
arXiv:2606.16011v2 Announce Type: replace Abstract: Standard accuracy benchmarks evaluate whether large language models (LLMs) reach correct answers. However, they do not test whether models maintain...
arXiv:2608.01291v2 Announce Type: replace Abstract: We present ArabicDialectSafety, a human-curated Arabic safety dataset of 25,071 prompts covering six Arabic varieties: Modern Standard Arabic, Syri...
arXiv:2608.24621v2 Announce Type: replace Abstract: Can language models be trusted in safety- critical operations? In such settings, strong per- formance on semantic metrics does not guaran- tee oper...
arXiv:2510.00628v3 Announce Type: replace-cross Abstract: Large audio-language models (LALMs) are often used in tasks that involve reasoning over ordered options. An open question is whether their pr...