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
60 results for “keyword:"counterfactual evaluation"” in ICLR 2027. 22 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When LLM Advice Depends on Values Users Never Stated: Measuring Undisclosed Preference Dependence▼1.2k1.67
[PDF]From Target Selection to Condition Reuse: Auditing Residual Interventions in Tool-Use Models▼4.3k2.00
[PDF]Necessity-Bench: A Self-Report-Free Test of Whether Vision-Language Model Answers Are Actually Grounded in Evidence▼1611.50
[PDF]When Do Behavior Traces Validate MoE Interventions? Auditing Labels, Selection, and Decision Impact▼5.8k2.33
[PDF]MoE Mirage: Selection Noise and Routing-Weight Geometry in Token-Level Counterfactuals▼1.2k3.00
[PDF]When Should Agents Differ? Learning to Schedule Behavioral Diversity from Training Dynamics in Multi-Agent RL▲3.0k2.33
[PDF]Credit Without Ground Truth: Claim-Matched Evaluation of Step-Level Credit with Finite Executed Replay▼1361.33
[PDF]When Should LLM Agents Talk? Measuring Coordination Value and Auditing Learned Routers▼4.3k2.00
[PDF]When Are Tool Calls Necessary? Counterfactual Evaluation and Pre-Generation Epistemic Gating in Tool-Augmented Language Models▼4.3k2.00
[PDF]Visual Evidence Under Cross-Examination: Evaluating and Controlling Decision-Level Evidence Use in Vision-Language Models▲3952.67
[PDF]Being Reasonable Is Not Enough: Measuring Selective Relationship Conditioning in Full-Duplex Speech Agents▼4.3k2.00
[PDF]Do Reinforcement Learning Controllers Use Live State? A Diagnostic for Metro Operations▼1361.33
[PDF]Diagnosing Temporal Instance-State Binding and Its Stage-Dependent Repairability in Vision-Language Models: A Controlled Study▼5.8k2.33
[PDF]What Can Large Language Models Discover from Experiments? Scientific Claims and Discovery Value across Multiple Worlds▼1611.50
[PDF]Counterfactual Tests Reveal Limited Depth-Image Use in RGB-D VLMs: A Probing and Causal-Patching Diagnosis on Metric-Distance Queries▲6.1k2.00
[PDF]When the Counterfactual Is Adjudicated: A Grid-Curtailment Benchmark Separating Structure from One-Sided Estimation▼1361.33
[PDF]Counterfactual Twins and Executable Validity Gates for Diagnosing Spatial Reasoning in Multimodal LLMs▲11.00
[PDF]When Should an AI Agent Change Its Mind? Counterfactual Evaluation of Multimodal Evidence Reasoning with Contrast-Persistence Tests▼1.2k1.67
[PDF]Benchmarking and Evaluating Implicit Biases in Single- and Multi-Agent Language Models▼5.8k2.33
[PDF]More Than Correct Answers: Testing, Tracing, and Predicting Multi-Hop Execution in Transformers▲6.1k2.00
[PDF]When Should the Decision Change? Counterfactual Probing of Vision-Language Models for Autonomous Driving▼4.3k2.00
[PDF]SpatialGraph-Eval: Intervention-Based Evaluation of Spatial-Network Reasoning in Multimodal Models▼1.2k1.67
[PDF]Sensitivity Before Connectivity: Minimal Pairs Reveal How CNNs Learn a Global Visual Rule▼4.3k2.00
[PDF]Measurement-Aligned Diffusion: Closing the Loop Between Generative Models and Catalog Measurements▼1.2k1.67
[PDF]IMPACT: Measuring Conditional Workflow Responses to Single-Span Model Substitution in Stateful LLM Agents▼1361.33
[PDF]From Activation to Specificity: Automating Counterfactual Testing of Visual Representations in the Human Brain▲3952.67
[PDF]EviPair: Paired Behavioral Diagnostics for Evidence-Responsive Decisions in Language Models▼5.8k2.33
[PDF]SQCAD: Lifecycle-Aware Authorization for Scope-Qualified Persistent Memory in Long-Term Agents▼3.7k2.25
[PDF]Does Assigned Identity Change How Language Models Use History? Separating Self-Binding from Focal-Agent Effects▼1.2k1.67