Artificial Intelligence

When Benchmarks Leak: Inference-Time Decontamination for LLMs ACL 2026 When Bigger Isn’t Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisation ACL 2026 When Can Transformers Count to n? UAI 2026 When Can We Learn from Noisy Logical Data? Parameterized Complexity of Approximate Concept Fitting in Description Logics UAI 2026 When Can We Trust LLMs in Mental Health? Large-Scale Benchmarks for Reliable LLM Evaluation EACL 2026 When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness CVPR 2026 When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure ACL 2026 When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents? ACL 2026 When Does Auxiliary Modality Matter in Solving Geometric Problems? A Comprehensive Study of Textual, Formal, and Visual Modalities EACL 2026 When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models ACL 2026 When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval ACL 2026 When Do Language Models Endorse Limitations on Human Rights Principles? EACL 2026 When Do Models Actually Decide? Mapping the Layer-Wise Decision Timeline in Pretrained Neural Networks CVPR 2026 When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents ACL 2026 When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models ACL 2026 When Environments Shift: Safe Planning with Generative Priors and Robust Conformal Prediction L4DC 2026 When Equal Isn’t Fair: Mitigating Over-Normalization in Large Language Models (Student Abstract) AAAI 2026 When Eyes and Ears Disagree: Can MLLMs Discern Audio-Visual Confusion? AAAI 2026 When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHF AAAI 2026 When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning ACL 2026 When Instinct Guides and Insight Grounds: Staged RL Training for LLM Agents AAAI 2026 When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning ACL 2026 When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges ACL 2026 When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors ACL 2026 When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters CVPR 2026