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.

Similar Papers

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF (2026.acl-long)

Copied to clipboard

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.
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.
In-Context Learning (and Unlearning) of Length Biases (2025.naacl-long)

Copied to clipboard

Challenge: Existing work has demonstrated the ability of large language models to learn lexical and label biases in-context negatively impacts performance and robustness of models.
Approach: They investigate the impact of length biases on in-context learning by analyzing model length information in-constext.
Outcome: The proposed model learns length biases in the context window without parameter updates.
Following Length Constraints in Instructions (2025.emnlp-main)

Copied to clipboard

Challenge: Existing instruction following models fail to follow length constraints in their evaluations.
Approach: They propose to train models that can be controlled at inference time with instructions containing desired length constraints.
Outcome: The proposed models outperform standard instruction following models in length instructed evaluations.
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.
Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) often produce unnecessarily long explanations that reduce efficiency.
Approach: They propose a length-aware reward that selectively penalizes insignificance tokens . they also propose 'dynamic length control' that encourages more detailed reasoning .
Outcome: The proposed method reduces response length while maintaining correctness, the authors show . it selectively penalizes insignificance tokens while maintaining accuracy .
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.
Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Reward hacking is a problem in reinforcement learning where the ability to specify the desired behavior of a reward function is difficult.
Approach: They propose to use feedback as a potential-based shaping function to solicit and apply feedback from large language models to improve convergence speed and policy returns.
Outcome: The proposed method improves convergence speed and policy returns over baselines even with significant ranking errors and eliminates the need for complex post-processing of reward functions.
Debiasing Large Language Models with Structured Knowledge (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods to reduce biases in pre-training models are hampered by their performance.
Approach: They propose a method that utilizes structured knowledge to mitigate bias in LLMs . their method obviates the need for training from scratch, thus offering enhanced scalability .
Outcome: The proposed method outperforms state-of-the-art (SOTA) baselines in the debiasing ability.

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