首页 > 专栏 > cs.CL updates on arXiv.org cs.CL updates on arXiv.org 共 4795 条资讯 GrepSeek: Training Search Agents for Direct Corpus Interaction 2026-06-28 03:07:22 Structure vs. Chain-of-Thought: Evaluating LLM Criteria Extraction for Depression Severity 2026-06-28 03:07:22 CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows? 2026-06-28 03:07:22 Atomic and Holistic LLM Judges for Reference-Grounded Support Labels: A Prompt-Controlled Comparison 2026-06-28 03:07:22 A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review 2026-06-28 03:07:22 Functional Subspace, where language models can use vector algebra to solve problems 2026-06-28 03:07:22 Evidence First, Arithmetic Second: A System Report and Failure Analysis for DocSem 2026-06-28 03:07:22 MedRECT: A Bilingual Medical Reasoning Benchmark for Error Correction in Clinical Texts 2026-06-28 03:07:22 The Invisible Language Tax: Token Premiums of French and Regional Languages in 2026 LLM Tokenizers, and a French-Optimized Prototype 2026-06-28 03:07:22 Voices of Freelance Professional Writers on AI: Limitations, Expectations, and Fears 2026-06-28 03:07:22 Settle: Learning When to Stop Reasoning 2026-06-28 03:07:22 Semifactual Credit-Augmented Policy Optimization 2026-06-28 03:07:22 When Clipping Reverses Correction: Failure Dynamics of Pointwise Forward-KL On-Policy Self-Distillation 2026-06-28 03:07:22 Fairness Beyond a Single Run: Training-Seed Variability in Speech LLM Adaptation 2026-06-28 03:07:22 Cheap to Draw, Expensive to Trust: Certifying Test-Time Scaling Curves 2026-06-28 03:07:22 Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment 2026-06-28 03:07:22 RoPE at the End of Its Rope? Theory, Diagnosis, and Mitigation of Long-Context Failures 2026-06-28 03:07:22 GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis 2026-06-28 03:07:22 Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard 2026-06-28 03:07:22 TRACE: Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction for LitTraceQA 2026-06-28 03:07:22 123…240下一页 » 相关分类 #!/slash/note #UNTAG (B)(F)uzzing on my world (Hi)story (IN)SECURE Magazine Notification (gdb) break *0x972 - 带鱼博客 BeltfishBlog - ./kwaa.dev .NET Blog .Trash /home/rook1e 00's Adventure 0kami's Blog 0x41414141 in ?? () 0x7f Blog 0xRick Owned Root ! 0xd00's blog 1 Byte 1A23 Blog 1A23 Studio 1Link.Fun 1stwebdesigner 251 2BAB 的工程博客 2ch中文网 360 CERT 360 Netlab Blog - Network Securi 38号车评中心 3o米的微博 404 Media