REVIEW 13 cited by
Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
read the original abstract
Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been effective in aligning LLMs with human preferences, it is susceptible to spurious correlations in reward modeling. Consequently, it often introduces biases-such as length bias, sycophancy, conceptual bias, and discrimination-that hinder the model's ability to capture true causal relationships. To address this, we propose a novel causal reward modeling approach that integrates causality to mitigate these spurious correlations. Our method enforces counterfactual invariance, ensuring reward predictions remain consistent when irrelevant variables are altered. Through experiments on both synthetic and real-world datasets, we show that our approach mitigates various types of spurious correlations effectively, resulting in more reliable and fair alignment of LLMs with human preferences. As a drop-in enhancement to the existing RLHF workflow, our causal reward modeling provides a practical way to improve the trustworthiness and fairness of LLM finetuning.
Forward citations
Cited by 13 Pith papers
-
What do Reward Models Memorize?
Counterfactual memorization maps show RMs misallocate capacity to easy pairs, memorize dataset artifacts, and overgeneralize length/compliance on unseen pairs.
-
Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure
Single-axis reward bias mitigations redirect optimization pressure to correlated proxies, and audit-distribution scoring produces identical observables for successful mitigation, bias substitution, and overcorrection.
-
Style over Substance: A Shortcut Audit of Emotion-Description Preference Evaluation
A content-blind probe using only description length and generator identity matches finetuned 7B multimodal judges on EmoPrefer, showing benchmark scores are reachable without video grounding.
-
General Preference Reinforcement Learning
GPRL carries k-dimensional skew-symmetric preference structure into policy updates via per-dimension advantages and context-dependent eigenvalues, yielding 56.51% length-controlled win rate on AlpacaEval 2.0 from Llam...
-
General Preference Reinforcement Learning
GPRL applies a k-dimensional preference model with per-dimension normalized advantages and a drift monitor to LLM post-training, reporting 56.51% length-controlled win rate on AlpacaEval 2.0 and gains on other benchma...
-
General Preference Reinforcement Learning
GPRL carries a k-dimensional skew-symmetric preference structure into policy updates with per-dimension advantages and a drift monitor, yielding 56.51% length-controlled win rate on AlpacaEval 2.0 from Llama-3-8B-Inst...
-
Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders
Sparse autoencoders isolate unstable features in reward model representations and enable two mitigation techniques that reduce preference errors on perturbed inputs without retraining.
-
Robust Reward Modeling for Large Language Models via Causal Decomposition
A decoder-based reconstruction error regularizer improves reward model accuracy on RewardBench from 0.832 to 0.868 while favoring shorter, less sycophantic outputs.
-
Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning
Group Causal Counterfactual Policy Optimization trains LLMs on generalizable reasoning by defining episodic rewards for counterfactual robustness and transferability then optimizing the policy with token-level advantages.
-
Factored Causal Representation Learning for Robust Reward Modeling in RLHF
A factored causal representation learning method improves robustness of reward models in RLHF by isolating causal factors from biases like length and sycophancy using adversarial gradient reversal.
-
Token-Level LLM Collaboration via FusionRoute
FusionRoute augments token-level expert routing with a trainable complementary logit generator to expand the policy class and recover optimal decoding under mild conditions, outperforming prior collaboration and mergi...
-
Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization
Proxy RL produces a staged proxy-internalization capability that emerges before and predicts reward hacking in coding environments.
-
Causality as the Statistical Conscience of Artificial Intelligence: From Pearl's Ladder to Trustworthy Machines
Causality is required for out-of-distribution generalization in AI, with a necessity theorem and unified causal estimators proposed to fix failure modes like hallucination and reward hacking.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.