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
1,440 results for “area:"interpretability and explainable AI"” in ICLR 2027. 337 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Content-Matched Is Not Lexically Matched: Text and Untrained-Network Baselines for Evaluation-Awareness Probing▼4.5k2.67
[PDF]Human Difficulty Is Not Task Difficulty: What Policy Representations Know Beyond an Optimal Solver▼1.2k1.67
[PDF]Reconstruction, Not Localization: A Mechanistic Account of Sparse-Feature OOD Detection in Vision Transformers▼1361.33
[PDF]Navigating the OCEAN: An Atlas of Big Five Personality Representations in Language Models▲8.9k2.75
[PDF]How Vision-Language Models Form Ambiguous Depth Interpretations: A Sparse Feature Analysis of Visual Evidence Transformation▼1.2k1.67
[PDF]Measure Once, Steer with Many: Context Contamination and Composite Control for Persona Drift in LLMs▼5.8k2.33
[PDF]Early Context Starvation in Conversational LLMs: Causal Evidence from Attention Interventions▼1.2k1.67
[PDF]Coordinate-Dependent Generalization in Transformers: Controlled Interventions and Prospective Prediction on Modular Arithmetic▼1.2k1.67
[PDF]Probing Under Distribution Shift: Learning Generalizable Distributed Representations of LLM Activations▼5.8k2.33
[PDF]Constructing Pareto Frontiers of Optimal Reasoning Termination Methods for Overthinking in Reasoning Models▼1.2k1.67
[PDF]Attention's Gravitational Field: A Power-Law and Linguistic Interpretation of Positional Correlation▼1361.33
[PDF]Disentangling Verbalized Evaluation Awareness and Refusal through Neuron-Level Intervention▼4.3k2.00
[PDF]Latent Assembly: Causal Discovery and Cross-Task Linking of Executable Operations in Language Models▲13k2.33
[PDF]Predicting Reasoning Errors Before They Occur: A Prompt-Side Activation Direction Anticipates Correctness in a Large Language Model▼1361.33
[PDF]Aggregation Order in Activation Patching: Which Circuit Is Selected and What It Preserves▼4.3k2.00
[PDF]Predictive Mechanistic Interpretability of Post-Training: A Priori Forecasts of Circuit Localization and Sign from the Base Model▼2.0k1.00
Withdrawn or desk rejected (337)
[PDF]Influential but Misaligned: LLM Evidence Drives Predictions Yet Misses What Institutions ClassifiedWithdrawn1.33
[PDF]Same Tokens, Different Readings: Representational and Causal Tests of Lexical-Unit Encoding in Language ModelsWithdrawn1.00
[PDF]What Pooled Explained Variance Can Hide: Evaluating Crosscoder Fidelity in Vision EncodersWithdrawn1.33
[PDF]The Influence Spectrum: The Power of Layer-Wise Importance in Large Language ModelsWithdrawn1.67
[PDF]Characterizing Errors in Small Medical Language Models: Geometry, Prediction, and Causal SensitivityWithdrawn1.67
[PDF]Position Still Matters: Localizing and Controlling Latent Positional Effects in LLM ComparisonsWithdrawn1.67