NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
80 results for “keyword:"hallucinations"” in ICLR 2027. 25 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]H-MPO: Hierarchical Multi-Response Preference Optimization with Modality-Guided Decoding for Omni Large Language Models▼5.8k2.33
[PDF]LinAlg-Bench: When LLMs Stop Computing — Structured Hallucination, Sign Drift, and Depth-Gated Collapse in Matrix Arithmetic▲11.00
[PDF]Beyond Relevance: State-Conditioned Consequence Modeling for Adaptive Retrieval-Augmented Generation▼1.2k1.67
[PDF]Distilling Answers, Discarding Uncertainty: Uncertainty Collapse in Sequence-Level Knowledge Distillation▼1.2k1.67
[PDF]When More Seeing Does Not Help: Understanding and Mitigating Hallucinations in Think-with-Images Models▲5103.00
[PDF]Inducing Hallucinations in Video Large Language Models by Exploiting Spatiotemporal Corruption Sensitivity▲3.0k2.33
[PDF]Alignment-State-Aware Preference Optimization for Mitigating Hallucinations in Multimodal Large Language Models▼4.3k2.00
[PDF]AeroProc-Bench: Distinct Citation and Safety Failures Create a Deployment Dilemma in Aviation Maintenance LLMs▲11.00
[PDF]TRACE: Tracing Representation Ancestry for Hallucination Mitigation in Large Vision-Language Models▲9.2k2.67
[PDF]Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations▲3952.67
[PDF]HalluClear: A Diagnostic and Evaluation Suite with Mitigation Probe for Hallucinations in GUI Agents▲4.6k3.00
[PDF]HARPS: Mitigating Multimodal Hallucinations via Head-Selective and Adaptive Perceptual Sink Reweighting▼3.7k2.25
Withdrawn or desk rejected (25)
[PDF]Rethinking Hallucination in Long-Video Understanding: A Unified Binding Perspective and a BenchmarkWithdrawn1.67
[PDF]The Filter Outweighs the Channel: Decomposing Why Tool-Using Agents Corrupt Structured Records at ScaleDesk rejected
[PDF]Believing Is Seeing: How VLMs Assemble Trust in an Image, and Where It Can Be ReadDesk rejected
[PDF]Beyond Model-Internal Signals: Steering VLLM Attention with Predicted Human SaliencyWithdrawn2.00
[PDF]SensiEdit: Sensitivity-Guided Spatial Attention Editing for Hallucination Mitigation in LVLMsWithdrawn1.33