Challenge: Existing approaches to tackling length bias are limited by their complexity or lack of a linear length-reward relation.
Approach: They propose a framework that learns and corrects underlying bias patterns by fitting a length-reward relationship into a reward model.
Outcome: The proposed framework improves length-controlled win rate and reduces verbosity without compromising performance.

Similar Papers

Beyond Excess and Deficiency: Adaptive Length Bias Mitigation in Reward Models for RLHF (2025.findings-naacl)

Copied to clipboard

Challenge: Existing efforts to mitigate length bias in reward models have decreased accuracy . achieving an automatic proxy that perfectly replicates human judgment is challenging in practice.
Approach: They propose an adaptive approach that dynamically adjusts the influence of response length in reward evaluations according to the context of the query.
Outcome: The proposed approach reduces unnecessary verbosity while improving overall response quality.
Disentangling Length from Quality in Direct Preference Optimization (2024.findings-acl)

Copied to clipboard

Challenge: Reinforcement Learning from Human Feedback (RLHF) exploits biases in human preferences, such as verbosity, and is under-explored for Direct Alignment Algorithms such as DPO.
Approach: They propose to exploit verbosity biases in RLHF by using direct preference optimization to fine-tune models.
Outcome: The proposed approach achieves 20% improvement in win rates when controlling for length on summarization and dialogue datasets, despite the GPT4 judge’s verbosity bias.
Removing Prompt-template Bias in Reinforcement Learning from Human Feedback (2025.findings-acl)

Copied to clipboard

Challenge: Reinforcement Learning from Human Feedback (RLHF) has shown promise for enhancing pre-trained large language models to generate responses that align with human preferences and societal values.
Approach: They propose a method to estimate prompt-template bias term during reward modeling and use it to calibrate reward scores.
Outcome: The proposed method can be flexibly combined with existing algorithms of removing length bias, leading to a further improvement in the aspect of enhancing the quality of generated responses.
Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback (2023.findings-emnlp)

Copied to clipboard

Challenge: Experimental results prove that language models can learn from human feedback better, irrespective of sequence length . emergence of length bias often induces the model to favor longer outputs .
Approach: They propose to separate reward modeling from the influence of sequence length by using the Product-of-Experts technique.
Outcome: The proposed approach shows that language models perform better regardless of sequence length . the main expert is focused on understanding human intents, while the biased expert targets the identification and capture of length bias.
Reward Difference Optimization For Sample Reweighting In Offline RLHF (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are becoming more capable, but their maximum likelihood objective for the next token prediction falls short in capturing such crucial human values.
Approach: They propose a reward difference prediction method that uses reward difference coefficients to reweigh sample pairs in offline RLHF and a difference model that considers rich interactions between a pair of responses.
Outcome: The proposed method is effective in both automatic metrics and human evaluation.
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies attributed verbosity to biased labels, but new research shows that DPO can be effective in mitigating verboses.
Approach: They propose to use a method to reduce the amount of verbosity in LLMs by using a downsampling approach.
Outcome: The proposed approach overcomes the problem of verbosity by reducing the length reliance of the proposed algorithm.
RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution (2025.emnlp-main)

Copied to clipboard

Challenge: Experimental results demonstrate the superiority of our approach to aligning large language models with human preferences.
Approach: They propose a method that evaluates and assigns specific credit to each token using an off-the-shelf reward model.
Outcome: The proposed method evaluates and assigns specific credit to each token using an off-the-shelf reward model.
CLHA: A Simple Yet Effective Contrastive Learning Framework for Human Alignment (2024.lrec-main)

Copied to clipboard

Challenge: Large language models (LLMs) have attracted considerable attention from academic and industrial communities due to their outstanding performance in various natural language processing tasks.
Approach: They propose a Contrastive Learning Framework for Human Alignment to evaluate the noise within the data and dynamically adjust the training process.
Outcome: The proposed framework surpasses other algorithms in terms of reward model scores, automatic evaluations, and human assessments on the widely used dataset "Helpful and Harmless"
Towards Reward Fairness in RLHF: From a Resource Allocation Perspective (2025.acl-long)

Copied to clipboard

Challenge: if rewards are imperfect, they can adversely affect the alignment of large language models (LLMs).
Approach: They propose a bias-agnostic method to address the issue of reward unfairness from a resource allocation perspective without specifically designing for each type of bias . they apply methods Fairness Regularization and Fairness Coefficient to achieve fairness in rewards.
Outcome: The proposed method achieves fairness in rewards while minimizing biases . it can be applied to verification and reinforcement learning scenarios .
Aligning to What? Limits to RLHF Based Alignment (2025.findings-naacl)

Copied to clipboard

Challenge: Existing studies on RLHF and covert and overt biases in large language models are unclear . et al. analyzed off-the-shelf language models to evaluate their overt and cover racial biase .
Approach: They evaluate the relationship between reinforcement learning from human feedback and biases in large language models.
Outcome: The proposed approach can be used to mitigat covert biases, the authors show . they found that the RLHF approach calcifies model biase .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations