Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 00023v1 Announce Type: cross Abstract: Dense sentence embeddings are fundamental to modern Retrieval-Augmented Generation (RAG) systems but suffer from a lack of interpretability due to feature superposition.
arXiv:2607. 00605v1 Announce Type: cross Abstract: Limited Memory Language Models (LMLMs) externalize factual knowledge to a database to enable deletion-based unlearning without retraining.
arXiv:2602. 21397v2 Announce Type: replace-cross Abstract: Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights.
arXiv:2607. 00001v1 Announce Type: new Abstract: Most approaches to AI alignment treat human preferences as fixed targets to be inferred and optimized.
arXiv:2511. 06701v3 Announce Type: replace-cross Abstract: AI-Scientist systems risk manufacturing spurious discoveries through uncontrolled multiple testing.
arXiv:2607. 00603v1 Announce Type: new Abstract: We give a descent-free, alignment-free measurement of singular structure on trained networks.
arXiv:2604. 17289v2 Announce Type: replace Abstract: Supervised fine-tuning of large language models relies on human-annotated data, yet annotation pipelines routinely involve multiple crowdworkers of heterogeneous expertise.
arXiv:2607. 00434v1 Announce Type: cross Abstract: Vision-language models (VLMs) have become a paradigm for multimodal learning, yet remain unstable due to object hallucination, weak visual grounding, and catastrophic forgetting after full-parameter instruction tuning.
arXiv:2607. 01083v1 Announce Type: cross Abstract: High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates.
arXiv:2607. 00010v1 Announce Type: cross Abstract: Conversational recommender systems (CRSs) are a core component of next-generation intelligent recommender systems because they enable users to actively elicit preferences, clarify intentions, and adapt recommendations in real time.
arXiv:2607. 00304v1 Announce Type: cross Abstract: The bias-reliability tradeoff conjectures that LLM evaluation systems are constrained in (gamma, H, CV) space, where evaluator coupling (gamma), strategy diversity (H), and small-sample measurement reliability (CV(N)) cannot be simultaneously optimized at fixed sample size N.
arXiv:2504. 06299v2 Announce Type: replace-cross Abstract: Multimodal prediction models based on imaging and clinical data are increasingly used for clinical decision support, yet their interpretability remains limited.
arXiv:2601. 08467v2 Announce Type: replace-cross Abstract: Distracted driving is a major cause of traffic collisions, calling for robust and scalable detection methods.
arXiv:2511. 04694v5 Announce Type: replace-cross Abstract: As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instructions from multiple sources within a single prompt context.
arXiv:2410. 22526v2 Announce Type: replace Abstract: To effectively address potential harms from Artificial Intelligence (AI) systems, it is essential to identify and mitigate system-level hazards.
arXiv:2607. 00089v1 Announce Type: new Abstract: Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact.
arXiv:2607. 00415v1 Announce Type: cross Abstract: Authority bias poses a critical safety concern in language models: models systematically prioritize social cues from authority figures over factual consistency, swaying their answers based on source credibility rather than evidence.
arXiv:2607. 00746v1 Announce Type: cross Abstract: The bird's-eye view (BEV) representation enables multi-sensor features to be fused within a unified space, serving as the primary approach for achieving comprehensive 3D perception.
arXiv:2607. 00144v1 Announce Type: cross Abstract: Active learning (AL) performance is known to be budget-dependent, yet regimes are typically defined by heuristic label counts that fail to generalize across datasets or architectures.
arXiv:2607. 00218v1 Announce Type: cross Abstract: Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories.