# Rethinking DPO: The Role of Rejected Responses in Preference Misalignment

arXiv: https://arxiv.org/abs/2506.12725 · HTML: https://mlsanity.com/paper/2506.12725/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 15 Jun 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 19 of 19)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study](https://mlsanity.com/paper/2404.10719/) (2024)
- [From r to Q^*: Your Language Model is Secretly a Q-Function](https://mlsanity.com/paper/2404.12358/) (2024)
- [Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive](https://mlsanity.com/paper/2402.13228/) (2024)
- [Self-Play Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2405.00675/) (2024)
- [Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data](https://mlsanity.com/paper/2404.14367/) (2024)
- [Understanding the performance gap between online and offline alignment algorithms](https://mlsanity.com/paper/2405.08448/) (2024)
- [Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer](https://mlsanity.com/paper/2405.16436/) (2024)
- [Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://mlsanity.com/paper/2406.09279/) (2024)
- [Preference Learning Algorithms Do Not Learn Preference Rankings](https://mlsanity.com/paper/2405.19534/) (2024)
- [Minor DPO reject penalty to increase training robustness](https://mlsanity.com/paper/2408.09834/) (2024)

## Built on by (most cited first, 15 of 15)

- [Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems](https://mlsanity.com/paper/2602.15198/) (2026)
- [Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models](https://mlsanity.com/paper/2511.03317/) (2025)
- [Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories](https://mlsanity.com/paper/2607.10601/) (2026)
- [Stable Preference Optimization: A Bilevel Approach to Catastrophic Preference Shift](https://mlsanity.com/paper/2507.07723/) (2025)
- [An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift](https://mlsanity.com/paper/2601.05882/) (2026)
- [Learning from Self Critique and Refinement for Faithful LLM Summarization](https://mlsanity.com/paper/2512.05387/) (2025)
- [Mitigating Mismatch within Reference-based Preference Optimization](https://mlsanity.com/paper/2602.11902/) (2026)
- [Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?](https://mlsanity.com/paper/2604.08723/) (2026)
- [Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models](https://mlsanity.com/paper/2605.02626/) (2026)
- [A Finetuned SpeechLLM for Joint Multi-Granular L2 Assessment and Natural-Language Rationales](https://mlsanity.com/paper/2606.09470/) (2026)
- [Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance](https://mlsanity.com/paper/2605.15012/) (2026)
- [Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs](https://mlsanity.com/paper/2606.12590/) (2026)
- [KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment](https://mlsanity.com/paper/2607.03166/) (2026)
- [PrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors](https://mlsanity.com/paper/2609.40165/) (2026)
- [TrustMI: Causally controlling how assistants trust their users](https://mlsanity.com/paper/2610.06064/) (2026)

## Abstract (arXiv)

Direct Preference Optimization (DPO) is a simple and efficient framework that has attracted substantial attention. However, it often struggles to meet its primary objectives -- increasing the generation probability of chosen responses while reducing that of rejected responses -- due to the dominant influence of rejected responses on the loss function. This imbalance leads to suboptimal performance in promoting preferred responses. In this work, we systematically analyze the limitations of DPO and existing algorithms designed to achieve the objectives stated above. To address these limitations, we propose Bounded-DPO (BDPO), a novel method that bounds the influence of rejected responses while maintaining the original optimization structure of DPO. Through theoretical analysis and empirical evaluations, we demonstrate that BDPO achieves a balanced optimization of the chosen and rejected responses, outperforming existing algorithms.