🤖 AI 前沿资讯

arXiv

What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models

Masked diffusion language models generate tokens in parallel, but their efficiency depends on which predictions are c...

AI 聚合

2026-10-23

arXiv

Who Is Sycophantic to Whom? Confident LLMs, Human Deference, and the Collapse of Trust Calibration

Research on sycophancy asks whether large language models (LLMs) bend towards what their users want to hear. We ask t...

AI 聚合

2026-10-23

arXiv

Would an LLM Match into a Residency? Uncertainty, Reasoning and Image Use of Open Language Models on the Spanish MIR Examination

Accuracy on medical examinations is common evidence offered for the clinical use of language models, yet a health sys...

AI 聚合

2026-10-23

arXiv

VERA: A Responsible AI Dashboard for Assessing LLM Deployments in Light of the EU AI Act

Institutions that deploy large language models in regulated settings often need technical evidence of responsible AI ...

AI 聚合

2026-10-23

arXiv

Simulated Control Evals

Control evaluations measure whether safeguards can prevent an AI model from causing undesired outcomes even when it i...

AI 聚合

2026-10-23

arXiv

How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions

Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (R...

AI 聚合

2026-10-23

arXiv

Questioning Instrumental Convergence in RLVR: Checkpoint Evidence from OLMo-3

Instrumental convergence is often invoked as a general reason to expect capable agents to acquire or express power-se...

AI 聚合

2026-10-23

arXiv

Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation

Chain-of-thought (CoT) prompting elicits step-by-step rationales that appear to explain model predictions, but there ...

AI 聚合

2026-10-23

arXiv

Low-Bit N-Gram Embeddings for Language Models

Many recent open-weight language models use n-gram embedding tables to improve performance. These tables store learne...

AI 聚合

2026-10-23

arXiv

EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence

Tool-using language model agents rely on environmental facts to decide whether an action is permitted. When a tool re...

AI 聚合

2026-10-23

arXiv

METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning

Meta-reinforcement learning aims to train agents that adapt quickly to unseen tasks from limited interaction, but thi...

AI 聚合

2026-10-23

arXiv

Cost-Aware Abstention for LLM-Based IT Ticket Classification

Wrong automatic routing of an IT support ticket can cost more than human triage. We evaluate cost-aware abstention as...

AI 聚合

2026-10-23