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
54 results for “keyword:"self consistency"” in ICLR 2027. 7 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Relative Capability Organizes the Geometry of Answer Distributions in Test-Time Scaling▼4.5k2.67
[PDF]Changing the Candidates, Not the Vote: A Repair Portfolio for Self-Consistency under a Per-Call Token Cap▼4.3k2.00
[PDF]When to Overrule the Majority Vote? Precision Under Disagreement in Test-Time Reasoning▼1.2k1.67
[PDF]When Should Self-Consistency Trust Trajectory Signals? Competition-Aware Reselection for LLM Reasoning▼1.2k1.67
[PDF]Consistency Checking in Interactive Narratives at Million-Token Scale: A Benchmark and a Dual-Route Evaluator▼12k1.67
[PDF]Beyond Symmetric Agents: Cognitive Diversity and Multiagent Debate in Small Language Models▼1.2k1.67
[PDF]Consensus Is Not Correctness: Reliability-Aware Self-Teaching for Unsupervised Self-Distillation▲11.20
[PDF]Beyond Self-Consensus: Mitigating Self-Reinforcing Exploration Bias in Test-Time Reinforcement Learning▼4.3k2.00
[PDF]TRUER: Test-Time Reward Correction Using an Error-Aware Rectifier for Reinforcement Learning▲6.1k2.00
[PDF]Reliability-Aware Bayesian Self-Consistency for Evidence Aggregation and Risk-Controlled Abstention▼4.3k2.00