Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| AI Can Be Easily Persuaded in Clinical Decision Making Fenglin Liu, Jiayuan Zhu, Jiazhen Pan, Junde Wu Published: 2026-08-29Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (94%) | 12 |
| Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration Ammar Mohanna, Mohamad Zbib Published: 2026-08-29Area: cs.CLCitations: 15 Tags: ai-safety, alignment-training, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R7 (92%) | 15 |
| A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability R. Thomas McCoy, Zhang Enyan Published: 2026-08-29Area: cs.CLCitations: - Tags: ai-safety, cscl, interpretability, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, interpretability, preprint | E12 / R8 (94%) | - |
| Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered Aryo Pradipta Gema, Neel Rajani, Pasquale Minervini, Rohit Saxena Published: 2026-08-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (88%) | - |
| Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered Aryo Pradipta Gema, Neel Rajani, Pasquale Minervini, Rohit Saxena Published: 2026-08-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, preprint | E13 / R10 (90%) | - |
| Detecting and Repairing Hallucinations in Retrieval-Augmented Generation Aske Plaat, Niki van Stein, Sai Krishna Reddy Mulakkayala Published: 2026-08-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (93%) | - |
| HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Grounding Che Hyun Lee, Dongwook Lee, Eunwoo Song, Heeseung Kim Published: 2026-08-29Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, preprint | E25 / R16 (91%) | 15 |
| Learning Simple Test-Time Environments for LLM Web Agents Junxuan Li, Ming Yan, Peng Li, Yang Liu Published: 2026-08-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (92%) | - |
| Not All or None: Dynamic Construction of Target-aware Memory Graph for Conversational Stance Detection Bin Liang, Kam-Fai Wong, Ruifeng Xu, Yifan Xiang Published: 2026-08-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (90%) | - |
| SHADOWBENCH: Toward Reliable Automatic Evaluation of Semantic Alignment in Autoformalization Donghoon Hyeon, Dongwook Cheon, Hojae Han, Jongyoon Kim Published: 2026-08-29Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint, safety-evaluation | 2026-08-29 | cs.CL | ai-safety, alignment-training, cscl, preprint, safety-evaluation | E8 / R7 (93%) | - |
| SHADOWBENCH: Toward Reliable Automatic Evaluation of Semantic Alignment in Autoformalization Donghoon Hyeon, Dongwook Cheon, Hojae Han, Jongyoon Kim Published: 2026-08-29Area: cs.CLCitations: 15 Tags: ai-safety, alignment-training, cscl, preprint, safety-evaluation | 2026-08-29 | cs.CL | ai-safety, alignment-training, cscl, preprint, safety-evaluation | E9 / R7 (92%) | 15 |
| StageWell: A Process-Aligned Chinese Corpus for Positive-Psychology Support Dialogue Bo Wang, Shiguang Ni, Yuxiong Wang, Yu Zhang Published: 2026-08-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, preprint | E10 / R16 (91%) | - |
| The Illusion of Replacement: Rethinking Specialized Machine Learning Models in the Foundation Model Era Kiyan Rezaee Published: 2026-08-29Area: cs.CLCitations: 159 Tags: ai-safety, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, preprint | E10 / R6 (89%) | 159 |
| The Illusion of Replacement: Rethinking Specialized Machine Learning Models in the Foundation Model Era Kiyan Rezaee Published: 2026-08-29Area: cs.CLCitations: 159 Tags: ai-safety, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, preprint | E16 / R8 (89%) | 159 |
| trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories Hadi Mohammadi Published: 2026-08-29Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, preprint | E11 / R6 (92%) | - |
| A Probabilistic Interpretation of KV Cache Eviction Aditya Grover, Alex Chen, Daniel Israel, Guy Van den Broeck Published: 2026-08-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | E7 / R6 (93%) | - |
| Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL Feiran Huang, Hao Chen, Jiayan Lin, Qinggang Zhang Published: 2026-08-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | - | - |
| A rigor-matched audit of periodic-step layer skipping for efficient llm inference: conflayers versus swift, with a supplemental analysis of trained routing alternatives Arpan Ghosh, Prateek Kumar Sikdar Published: 2026-08-28Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | E11 / R8 (94%) | 15 |
| BanglaMed-QA: A Question Answering System for Healthcare Support in Bangla Abdullah Al Shafi, Atia Shahnaz Ipa, K. M. Azharul Hasan, Rowzatul Zannat Published: 2026-08-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | - | - |
| Embedding Models for Stance-Aware Argument Retrieval Adam Dejl, Angelo Sparacino, Francesca Toni Published: 2026-08-28Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | E11 / R7 (91%) | 45 |
| Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction Meng-Hsuan Lin, Qing Ye Published: 2026-08-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | - | - |
| LandingAgent: A Reference-Annotated Dataset and Agentic Generation Framework for Landing Pages HyeongSeok Lee, Injun Baek, Junhoo Lee, Nojun Kwak Published: 2026-08-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | E18 / R16 (88%) | - |
| Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation Roberto I. Ono Filho Published: 2026-08-28Area: cs.CLCitations: 17 Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (90%) | 17 |
| Nested Byte-Level Vocabularies Are Cheap to Deploy and Expensive to Share: A Pre-Registered Negative Result Christos Koutsiaris Published: 2026-08-28Area: cs.CLCitations: 7 Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (91%) | 7 |
| NL2AGBench: Benchmarking LLM Auto-Formalization for AlphaGeometry Judy Song, Rory Hu, Samuel Xiao, Ziliang Zong Published: 2026-08-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | - | - |
| No Detectable Change in Side-Level WER from Prompt-Level Context: A Preregistered Ablation on a Production Oral-History Corpus Keith Nore, Stephanie Dodson, Theodore O. Cochran Published: 2026-08-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | E9 / R6 (93%) | - |
| OpenStamp: A Watermark for Open-Source Language Models Danish Pruthi, Miroojin Bakshi, Saksham Rastogi Published: 2026-08-28Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (93%) | 15 |
| SimpCue: Cue-Based Prompting for Multilingual Text Simplification Horacio Saggion, Mehrzad Tareh, Stefan Bott Published: 2026-08-28Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | E15 / R14 (93%) | - |
| Synthetic Linguistic Agency: How an Embodied Mortal Agent Learns Linguistic Affordances through Consequential Social Experience Sixin Chen, Taizhou Chen Published: 2026-08-28Area: cs.CLCitations: 30 Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (94%) | 30 |
| Text Restoration of Ancient Documents with Language Models Annafelicia Zuffrano, Edoardo Caraffa, Giovanni Colavizza, Maddalena Modesti Published: 2026-08-28Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-08-28 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (92%) | 45 |