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
21 results for “keyword:"circuit discovery"” in ICLR 2027. 8 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Aggregation Order in Activation Patching: Which Circuit Is Selected and What It Preserves▼4.3k2.00
[PDF]Same Task, Different Answer: Persona Conditioning Modulates Shared Task Mechanisms in Language Models▼4.5k2.67
[PDF]Attribution-guided Pruning for Circuit Discovery and Targeted Correction in Language Models▼4.3k2.00
[PDF]CircuitFACT: Circuit Discovery for Mechanistic Interpretability of Graph Neural Networks▲3.0k2.33
[PDF]Tracing the Causal Transition from Event Relations to Moral Judgment in Language Models▼1.2k1.67
[PDF]How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits▲5103.00
[PDF]Do We Need Handcrafted Corruptions? Context-Preserving Activation Perturbation in Representation Space▼4.5k2.67
[PDF]Weight-Dictionary Decomposition: Reading a Transformer's Residual Stream with Its Own Writes▼1361.33
Withdrawn or desk rejected (8)
[PDF]Dynamic Mechanistic Interpretability for Real-Time State Transitions in World Models: Tracking Thoughts in MotionsDesk rejected
[PDF]Causal Differential Skill Circuits for Localizing and Repairing Bias in Tool-Using AgentsWithdrawn1.67
[PDF]Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic InterpretabilityWithdrawn1.33