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
689 results for “keyword:"mechanistic interpretability"” in ICLR 2027. 142 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Bidirectional Causal Tracing and Intervention: Causal Mechanism-Guided Machine Unlearning▼4.3k2.00
[PDF]Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models▼1.2k1.67
[PDF]Answer Candidates Reshape Language Model Decisions: Layer-wise Dynamics and Causal State Interventions▲6.1k2.00
[PDF]Localization Does Not Guarantee Control: Gate Failure and Partial Activation Steering in a Causal Reasoning Model▼1.2k1.67
[PDF]Training Selects Among Behaviorally Equivalent Computations in In-Context Dictionary Learning▲5.4k3.00
[PDF]A Polanyi-Like Paradox in Large Language Models: The Gap Between Spatial Representation and Decision▼5.8k2.33
[PDF]Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space▲3952.67
[PDF]Extracting and Composing Function Vectors for Analogical Reasoning over Latent Relations▲9.2k2.67
[PDF]PersJEPA: Interpretable Language Model Personalization through Sparse Residual Prediction▼1.2k1.67
[PDF]Eliciting LLM Propositional Beliefs in Agentic Tasks: Consistency, Accuracy, and Response Tendencies▲5103.00
[PDF]Why Do Language Models Take Shortcuts? A Mechanistic Account of Heuristic–Constraint Competition
Withdrawn or desk rejected (142)
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67
[PDF]Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of ReadoutWithdrawn