No article text was recorded for this version.
verbosity bias (length-based reward hacking)
Version 1 of 1276 papers375 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Long Way to Go: Investigating Length Correlations in RLHF
- Blog: Mitigating Length Bias in RLHF Through a Causal Lens
- Blog: Bias Fitting to Mitigate Length Bias of Reward Model in RLHF
- Blog: Length Desensitization in Directed Preference Optimization
- Blog: Understanding R1-Zero-Like Training: A Critical Perspective
- Blog: Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey
- Blog: A Long Way to Go: Investigating Length Correlations in RLHF
- Blog: ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO
- Blog: Reward Hacking in Rubric-Based Reinforcement Learning
- Blog: Investigating the effectiveness of length based rewards in DPO for building Conversational Financial Question Answering Systems
- Blog: ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback
- Blog: Understanding R1-Zero-Like Training: A Critical Perspective
- Blog: Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study
- Blog: Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback
- Blog: A Comprehensive Survey of Datasets, Theories, Variants, and Applications in Direct Preference Optimization
- Blog: Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch
- Blog: Preference Learning Unlocks LLMs' Psycho-Counseling Skills
- Blog: Verbosity Bias in Preference Labeling by Large Language Models
- Blog: Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
- Blog: Crosslingual Generalization through Multitask Finetuning
- Blog: RewardAnything: Generalizable Principle-Following Reward Models
- Blog: Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
- Blog: Concise Reasoning via Reinforcement Learning
- Blog: Unlocking Recursive Thinking of LLMs: Alignment via Refinement
- Blog: Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
- Blog: InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model
- Blog: Exploring the Secondary Risks of Large Language Models
- Blog: Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?
- Blog: Over-Reasoning and Redundant Calculation of Large Language Models
- Blog: CheXalign: Preference fine-tuning in chest X-ray interpretation models without human feedback
- Blog: Evaluating Creative Short Story Generation in Humans and Large Language Models
- Blog: HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
- Blog: Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level
- Blog: Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
- Blog: Understanding Reference Policies in Direct Preference Optimization
- Blog: Evaluation of Best-of-N Sampling Strategies for Language Model Alignment
- Blog: Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization
- Blog: MWPO: Enhancing LLMs Performance through Multi-Weight Preference Strength and Length Optimization
- Blog: Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
- Blog: Inference-Time Scaling for Generalist Reward Modeling
- Blog: Crosslingual Generalization through Multitask Finetuning
- Blog: GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents
- Blog: Promoting Efficient Reasoning with Verifiable Stepwise Reward
- Blog: Multi-Objective Linguistic Control of Large Language Models
- Blog: VPO: Leveraging the Number of Votes in Preference Optimization
- Blog: RLHF Workflow: From Reward Modeling to Online RLHF
- Blog: RLHF Workflow: From Reward Modeling to Online RLHF
- Blog: RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization
- Blog: Bootstrapping Language Models with DPO Implicit Rewards
- Blog: RLMR: Reinforcement Learning with Mixed Rewards for Creative Writing
- Blog: A Survey of Direct Preference Optimization
- Blog: Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
- Blog: Bootstrapping Language Models with DPO Implicit Rewards
- Blog: Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2
- Blog: AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling
- Blog: A Focused Study on Sequence Length for Dialogue Summarization
- Blog: Multi-Objective Linguistic Control of Large Language Models
- Blog: Disentangling Length Bias in Preference Learning via Response-Conditioned Modeling
- Blog: Gibbs Sampling from Human Feedback: A Provable KL- constrained Framework for RLHF
- Blog: Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference
Showing 60 of 276 papers.
History & citation
Current · Permanent link
- Verbosity Bias in Preference Learning merged into this direction (60% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_verbosity_bias_length_based_reward_hacki_8ae0ee56,
title = {verbosity bias (length-based reward hacking)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/verbosity-bias-length-based-reward-hacking/rdr_8ae0ee5623e64118b7469e07c40da3ad},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_verbosity_bias_length_based_reward_hacki_8ae0ee56_v1,
title = {verbosity bias (length-based reward hacking)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/verbosity-bias-length-based-reward-hacking/rdr_8ae0ee5623e64118b7469e07c40da3ad/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}