REFORM uses reward-guided controlled decoding to generate preference-class-consistent responses that the reward model mis-scores, then retrains the reward model on these failure modes to improve robustness.
Findings of the Association for Computational Linguistics: EMNLP , pages =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
CoLD mitigates length bias in process reward models for mathematical reasoning via counterfactual guidance, length penalties, bias estimation, and joint training, improving step selection accuracy and conciseness on MATH500 and GSM-Plus while boosting downstream RL performance.
Introduces secondary risks as a new class of LLM failures from benign prompts, defines two primitives, proposes SecLens search framework, and releases SecRiskBench showing risks are widespread across 16 models.
DynaCF dynamically downweights shortcut-sensitive samples in reward model training by tracking margin shifts under online counterfactual perturbations within the Bradley-Terry loss.
citing papers explorer
-
Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling
REFORM uses reward-guided controlled decoding to generate preference-class-consistent responses that the reward model mis-scores, then retrains the reward model on these failure modes to improve robustness.
-
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
CoLD mitigates length bias in process reward models for mathematical reasoning via counterfactual guidance, length penalties, bias estimation, and joint training, improving step selection accuracy and conciseness on MATH500 and GSM-Plus while boosting downstream RL performance.
-
Exploring the Secondary Risks of Large Language Models
Introduces secondary risks as a new class of LLM failures from benign prompts, defines two primitives, proposes SecLens search framework, and releases SecRiskBench showing risks are widespread across 16 models.
-
DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity
DynaCF dynamically downweights shortcut-sensitive samples in reward model training by tracking margin shifts under online counterfactual perturbations within the Bradley-Terry loss.