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 |
|---|---|---|---|---|---|
| Task-guided cross-subject latent alignment: a multi-encoder-decoder VAE Angeliki Papathanasiou, Jascha Achterberg, Rui Ponte Costa, Thomas E. Nichols Published: 2026-06-14Area: q-bio.NCCitations: - Tags: ai-safety, alignment-training, preprint, q-bionc | 2026-06-14 | q-bio.NC | ai-safety, alignment-training, preprint, q-bionc | E7 / R4 (96%) | - |
| Vernier: Probing Representational Misalignment Behind Lexical Gaps in Causal Reasoning Zhenyu Yu Published: 2026-06-14Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-06-14 | cs.CL | ai-safety, alignment-training, cscl, preprint | E8 / R4 (94%) | - |
| CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment Bin Chen, Bohua Wang, Hao Fang, Hao Wu Published: 2026-06-13Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-06-13 | cs.CL | ai-safety, alignment-training, cscl, preprint | E8 / R5 (96%) | - |
| Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment Jiawen Zhang, Lipeng He, N. Asokan, Yihan Wang Published: 2026-06-13Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-06-13 | cs.CR | ai-safety, alignment-training, cscr, preprint | E8 / R4 (97%) | - |
| Landmark-free Assessment of Lower-limb Alignment with Implicit Neural Shape Functions from Knee Radiographs Aleksei Tiulpin, Antti Kemppainen, Claudia Lindner, David Johnson Published: 2026-06-13Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-06-13 | cs.CV | ai-safety, alignment-training, cscv, preprint | E8 / R5 (95%) | - |
| The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment Christopher C. Yang, Xiaoyang Wang Published: 2026-06-07Area: cs.MACitations: - Tags: ai-safety, alignment-training, csma, preprint | 2026-06-07 | cs.MA | ai-safety, alignment-training, csma, preprint | E10 / R10 (92%) | - |
| Review Arcade: On the Human Alignment and Gameability of LLM Reviews Hans Ole Hatzel, Jan Strich, Sebastian Steindl Published: 2026-05-27Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-05-27 | cs.AI | ai-safety, alignment-training, csai, preprint | E10 / R8 (92%) | - |
| Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces Cameron Crow, Chi Jin, Seth Karten Published: 2026-05-17Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-05-17 | cs.LG | ai-safety, alignment-training, cslg, preprint | E12 / R10 (94%) | - |
| Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics Cristiano De Nobili Published: 2026-05-11Area: cond-mat.stat-mechCitations: - Tags: ai-safety, alignment-training, cond-matstat-mech, preprint | 2026-05-11 | cond-mat.stat-mech | ai-safety, alignment-training, cond-matstat-mech, preprint | E10 / R9 (95%) | - |
| Conformity Generates Collective Misalignment in AI Agents Societies Alessandro Bellina, Claudio Castellano, David Garcia, Giordano De Marzo Published: 2026-05-11Area: physics.soc-phCitations: - Tags: ai-safety, alignment-training, physicssoc-ph, preprint | 2026-05-11 | physics.soc-ph | ai-safety, alignment-training, physicssoc-ph, preprint | E6 / R5 (90%) | - |
| Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment Biao Liu, Ning Xu, Wenzhe Xu, Xin Geng Published: 2026-04-27Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-27 | cs.LG | ai-safety, alignment-training, cslg, preprint | E7 / R5 (97%) | - |
| The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers Benjamin Minhao Chen, Xinyu Xie Published: 2026-04-27Area: cs.CYCitations: - Tags: ai-safety, alignment-training, cscy, preprint | 2026-04-27 | cs.CY | ai-safety, alignment-training, cscy, preprint | E9 / R3 (95%) | - |
| Pref-CTRL: Preference Driven LLM Alignment using Representation Editing Imranul Ashrafi, Inigo Jauregi Unanue, Massimo Piccardi Published: 2026-04-26Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-26 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R5 (100%) | - |
| Beyond Single-Agent Alignment: Preventing Context-Fragmented Violations in Multi-Agent Systems Jie Wu, Ming Gong Published: 2026-04-24Area: cs.MACitations: - Tags: ai-safety, alignment-training, csma, preprint | 2026-04-24 | cs.MA | ai-safety, alignment-training, csma, preprint | E7 / R4 (99%) | - |
| C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMs Morteza Ziyadi, Rui Gao, Swastik Roy, Xiang 'Anthony' Chen Published: 2026-04-24Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-24 | cs.LG | ai-safety, alignment-training, cslg, preprint | E9 / R7 (98%) | - |
| Alignment has a Fantasia Problem Ashia Wilson, Mitchell Gordon, Nathanael Jo, Zoe De Simone Published: 2026-04-23Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-23 | cs.AI | ai-safety, alignment-training, csai, preprint | E10 / R5 (94%) | - |
| CAP: Controllable Alignment Prompting for Unlearning in LLMs Guangchun Luo, Hongli Pu, Jie Ou, Jingwen Pu Published: 2026-04-23Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-23 | cs.LG | ai-safety, alignment-training, cslg, preprint | E9 / R5 (97%) | - |
| CAP: Controllable Alignment Prompting for Unlearning in LLMs Guangchun Luo, Hongli Pu, Jie Ou, Jingwen Pu Published: 2026-04-23Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-23 | cs.LG | ai-safety, alignment-training, cslg, preprint | E9 / R5 (97%) | - |
| MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment Cam-Tu Nguyen, Chuanghao Ding, Juan Li, Xujie Zhang Published: 2026-04-23Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-04-23 | cs.CV | ai-safety, alignment-training, cscv, preprint | E11 / R7 (99%) | - |
| AI Governance under Political Turnover: The Alignment Surface of Compliance Design Andrew J. Peterson Published: 2026-04-22Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-22 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R4 (94%) | - |
| Can "AI" Be a Doctor? A Study of Empathy, Readability, and Alignment in Clinical LLMs Antonio Romano, Francesco Di Serio, Giuseppe Riccio, Marco Postiglione Published: 2026-04-22Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-22 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R4 (94%) | - |
| Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem Travis LaCroix Published: 2026-04-22Area: cs.CYCitations: - Tags: ai-safety, alignment-training, cscy, preprint | 2026-04-22 | cs.CY | ai-safety, alignment-training, cscy, preprint | E10 / R7 (98%) | - |
| Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models Inderjeet Nair, Jie Ruan, Lu Wang Published: 2026-04-22Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-22 | cs.AI | ai-safety, alignment-training, csai, preprint | E6 / R4 (96%) | - |
| Cognitive Alignment At No Cost: Inducing Human Attention Biases For Interpretable Vision Transformers Ethan Knights Published: 2026-04-21Area: cs.CVCitations: - Tags: ai-safety, alignment-training, cscv, preprint | 2026-04-21 | cs.CV | ai-safety, alignment-training, cscv, preprint | E8 / R5 (97%) | - |
| Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents Vasundra Srininvasan Published: 2026-04-21Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-21 | cs.AI | ai-safety, alignment-training, csai, preprint | E7 / R4 (98%) | - |
| Reasoning-Aware AIGC Detection via Alignment and Reinforcement Jianxun Lian, Max Xiong, Zhao Wang, Zhicheng Dou Published: 2026-04-21Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-21 | cs.AI | ai-safety, alignment-training, csai, preprint | E10 / R5 (99%) | - |
| Reasoning Structure Matters for Safety Alignment of Reasoning Models Chanyoung Park, Sangwu Park, Wonjoong Kim, Yeonjun In Published: 2026-04-21Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-04-21 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R6 (95%) | - |
| Self-Improving Tabular Language Models via Iterative Group Alignment Alexandra Brintrup, Mario Fritz, Tejumade Afonja, Yunbo Long Published: 2026-04-21Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-04-21 | cs.LG | ai-safety, alignment-training, cslg, preprint | E9 / R5 (96%) | - |
| Sherpa.ai Privacy-Preserving Multi-Party Entity Alignment without Intersection Disclosure for Noisy Identifiers Daniel M. Jimenez-Gutierrez, Enrique Zuazua, Georgios Kellaris, Joaquin Del Rio Published: 2026-04-21Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-04-21 | cs.CR | ai-safety, alignment-training, cscr, preprint | E7 / R4 (96%) | - |
| Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment Bobo Li, Hao Fei, Meishan Zhang, Min Zhang Published: 2026-04-21Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-04-21 | cs.CL | ai-safety, alignment-training, cscl, preprint | E8 / R5 (96%) | - |