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1,440 results for “area:"interpretability and explainable AI"” in ICLR 2027. 337 withdrawn or desk rejected listed apart.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]When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety▼5.8k2.33
[PDF]Antecedent-Aligned Rule Transfer with Partial-Overlap Consequent Fusion for Multi-Center TSK Fuzzy Classification▼4.3k2.00
[PDF]How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines▼1.1k3.25
[PDF]Affine Anticipation: LLM Answer Representations Are Largely Linearly Predictable from Context▼4.3k2.00
[PDF]Right Direction, Wrong Step: Geometric Analysis of Finite-Step Failure in Looped Transformers▲3.0k2.33
[PDF]Pinpoint Quantization: A Mechanistic Account of Tail-Capability Failures in Quantized LLMs▲5103.00
[PDF]Actions Speak Louder Than Frames: Quantifying Static and Temporal Reliance In Activity Recognition▲3.0k2.33
[PDF]From Agent Failures to Faulty Directives: Attribution-Based Aggregate Analysis of Skill Files▼4.3k2.00
[PDF]Trace Before You Conclude: Learning Evidential Reasoning for Industrial Maintenance Report Generation▼4.3k2.00
[PDF]Don't Ignore Them: Scaffold Features Matter for Stable SAE Steering in Diffusion Models▲3952.67
[PDF]Towards Co-Discovery By Extracting A Symbolic Representation From A Network Layer: Complexity, Algorithms and Experiments▼1361.33
[PDF]Localization Does Not Imply Steerability: A Mechanistic Study of Sign Errors in LLM Mathematics▼1361.33
[PDF]What Goes Up Should Come Down: A Training-Distribution Control for Interpretability Metrics▲5103.00
[PDF]Steering Vectors Can Control What Models Learn in Supervised Fine-Tuning: An Analysis of Behavior Offloading▼1.2k1.67
[PDF]Matryoshka attribution: Learning to attribute language model outputs to representations and weights▲2623.67
[PDF]Distributed Geographic Identity Encoding in Vision-Language Models: From Linear Probing to Sparse Autoencoder Feature Ablation, and Why Post-Hoc Debiasing Fails▲11.00
[PDF]Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy▼4.5k2.25
[PDF]Holding the Answer Fixed: What Hidden-State Probes and Interventions Establish About Correctness▼4.3k2.00
[PDF]CRANE: Functional Selectivity of Language-Conditioned Neurons in Multilingual Large Language Models▼1.2k1.67
[PDF]Not Which Path, but What Happens Before You Would Stop: What Reasoning Post-Training Changes▼1361.33
Withdrawn or desk rejected (337)
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]Retrieval-Augmented Anatomy-Aware Reasoning for Interpretable Alzheimer's DiagnosisWithdrawn1.33
[PDF]Spectral Invariants of Reasoning Trajectories: A Koopman‑DMD Dynamical View on LLM Internal Logic GeometryWithdrawn1.50
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67