Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2603. 09986v3 Announce Type: replace-cross Abstract: Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious problem within natural language processing for which we do not yet have an effective solution to mitigate against.
arXiv:2608. 03803v1 Announce Type: cross Abstract: Multilingual language models are deployed across a hundred or more languages, yet most benchmarks test whether a model can perform a task _in_ a language rather than whether it commands the language itself, conflating fluency with proficiency.
arXiv:2602. 07216v2 Announce Type: replace Abstract: Neural combinatorial optimization (NCO) trains fast heuristics for routing problems, but planners often need more than a single solve: they ask which stop to drop, which transition to preserve, or which subset of stops to remove if a route is infeasible.
arXiv:2608. 03218v1 Announce Type: cross Abstract: Dataset distillation compresses a large training set into a compact synthetic set while retaining its downstream utility.
arXiv:2608. 03294v1 Announce Type: new Abstract: We study the problem of learning multi-head softmax attention from black-box input-output access.
arXiv:2603. 09234v2 Announce Type: cross Abstract: Achieving high perceptual quality without hallucination remains a challenge in generative speech enhancement (SE).
arXiv:2602. 14735v2 Announce Type: replace-cross Abstract: The performance of quantum classifiers is typically analyzed through global state distinguishability or the trainability of variational models.
arXiv:2608. 03044v1 Announce Type: cross Abstract: Large language models are increasingly used to simulate human opinions, but prior work reports conflicting results: some studies find promising alignment with human survey data, while others find persona collapse and weak demographic sensitivity.
arXiv:2608. 02616v1 Announce Type: cross Abstract: We present the first independent, systematic evaluation of OpenAI's Privacy Filter (OPF), a 1.
arXiv:2608. 03611v1 Announce Type: new Abstract: Multimodal Sentiment Analysis (MSA) integrates text, audio, and vision to infer human affect, yet real-world multimodal observations are often incomplete.
arXiv:2608. 02660v1 Announce Type: cross Abstract: Advanced AI assistants engage users in extended interactions across a widening range of roles, including advice, decision support, collaboration, learning, emotional support, and companionship among others.
arXiv:2608. 03782v1 Announce Type: new Abstract: Hallucination remains a critical challenge for developing trustworthy Multimodal Large Language Models (MLLMs).
arXiv:2608. 03087v1 Announce Type: cross Abstract: Fine-grained energy consumption data are essential for applications such as demand forecasting, demand response planning, and grid reliability assessment.
arXiv:2608. 03875v1 Announce Type: cross Abstract: Designing effective reward functions remains a major bottleneck in Reinforcement Learning (RL).
arXiv:2604. 23954v2 Announce Type: replace Abstract: Artificial Intelligence (AI) and Machine Learning (ML) models used in clinical settings are increasingly deployed to support clinical decision-making.
arXiv:2511. 21214v4 Announce Type: replace-cross Abstract: Explicit safety policies can improve reasoning-model safety, but their effective coverage may lag behind evolving jailbreak strategies.
arXiv:2608. 00076v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) increasingly support high-stakes decision making by combining complementary information from images and text.
arXiv:2605. 27642v2 Announce Type: replace-cross Abstract: Soft prompting, also known as continuous prompting, is a parameter-efficient method for tuning LLMs to specific tasks.
arXiv:2508. 20697v4 Announce Type: replace Abstract: As large language models (LLMs) continue to grow in capability, so do the risks of harmful misuse through fine-tuning.
arXiv:2608. 02621v1 Announce Type: cross Abstract: Legal benchmarks typically score final answers even when models also state legal authority.