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
1,261 results for “keyword:"interpretability"” in ICLR 2027. 264 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision–Language Models▼4.5k2.67
[PDF]Programmable Semantic Interventions: Learning Causal Carriers from Behavioral Programs▲6.1k2.00
[PDF]Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls▲3.0k2.33
[PDF]The Model Already Has a Dictionary: Cumulative SVD Features as a Training-Free Alternative to Sparse Autoencoders▲3952.67
[PDF]Same Task Performance, Different Intervention Readouts: Cross-Run Variation under In-Context Rule Aliasing▲3.0k2.33
[PDF]RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback▲5103.00
[PDF]Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures▼4.3k2.00
[PDF]Beyond Output-Level Guidance: Leveraging Internal Exploration for LLM Self-Distillation▲5.4k3.00
[PDF]The complexity of understanding: Formalizing Concept Discovery in Mechanistic Interpretability▼1.2k1.67
[PDF]When Evidence Fails to Persuade: Tracing Internal Resistance to Evidence-Driven Preference Revision▲8.9k2.75
[PDF]When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs▼1.2k1.67
[PDF]A General Model Diffing Framework for Understanding Post-Training: Attributing Behavioral Differences to Parameter Updates▼1.2k1.67
[PDF]Affine Anticipation: LLM Answer Representations Are Largely Linearly Predictable from Context▼4.3k2.00
[PDF]Pinpoint Quantization: A Mechanistic Account of Tail-Capability Failures in Quantized LLMs▲5103.00
[PDF]Representation Without Disposition: Secret Loyalties Install as Preference but Not as Action, and What That Costs White-Box Audits▲3.0k2.33
[PDF]Hard to Remove, Cheap to Replace: Compact, Transferable Surrogates for Sensitive LLM Layers▲6.1k2.00
Withdrawn or desk rejected (264)
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33