# Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss

arXiv: https://arxiv.org/abs/2312.16682 · HTML: https://mlsanity.com/paper/2312.16682/

## Key facts

- Cited by 108 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 25 of its 39 references that are in the map.
- First posted on arXiv 27 Dec 2023.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [Statistical Rejection Sampling Improves Preference Optimization](https://mlsanity.com/paper/2309.06657/) (2023)
- [BASE Layers: Simplifying Training of Large, Sparse Models](https://mlsanity.com/paper/2103.16716/) (2021)
- [BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage](https://mlsanity.com/paper/2208.03188/) (2022)
- [Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training](https://mlsanity.com/paper/1911.03860/) (2019)
- [RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment](https://mlsanity.com/paper/2307.12950/) (2023)
- [Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning](https://mlsanity.com/paper/2306.03350/) (2023)
- [The CRINGE Loss: Learning what language not to model](https://mlsanity.com/paper/2211.05826/) (2022)
- [DIRECTOR: Generator-Classifiers For Supervised Language Modeling](https://mlsanity.com/paper/2206.07694/) (2022)
- [A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration](https://mlsanity.com/paper/2205.02517/) (2022)
- [Improving Open Language Models by Learning from Organic Interactions](https://mlsanity.com/paper/2306.04707/) (2023)

## Built on by (most cited first, 30 of 108)

- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts](https://mlsanity.com/paper/2406.12845/) (2024)
- [RLHF Workflow: From Reward Modeling to Online RLHF](https://mlsanity.com/paper/2405.07863/) (2024)
- [Direct Language Model Alignment from Online AI Feedback](https://mlsanity.com/paper/2402.04792/) (2024)
- [Iterative Reasoning Preference Optimization](https://mlsanity.com/paper/2404.19733/) (2024)
- [Self-Play Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2405.00675/) (2024)
- [Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications](https://mlsanity.com/paper/2402.05162/) (2024)
- [Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge](https://mlsanity.com/paper/2407.19594/) (2024)
- [A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity](https://mlsanity.com/paper/2401.01967/) (2024)
- [Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences](https://mlsanity.com/paper/2404.03715/) (2024)
- [A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce](https://mlsanity.com/paper/2504.11343/) (2025)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://mlsanity.com/paper/2503.15478/) (2025)
- [Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF](https://mlsanity.com/paper/2405.21046/) (2024)
- [Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision](https://mlsanity.com/paper/2403.09472/) (2024)
- [mDPO: Conditional Preference Optimization for Multimodal Large Language Models](https://mlsanity.com/paper/2406.11839/) (2024)
- [Enhancing Large Vision Language Models with Self-Training on Image Comprehension](https://mlsanity.com/paper/2405.19716/) (2024)
- [MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series](https://mlsanity.com/paper/2405.19327/) (2024)
- [Building Math Agents with Multi-Turn Iterative Preference Learning](https://mlsanity.com/paper/2409.02392/) (2024)
- [Aligning Large Language Models with Representation Editing: A Control Perspective](https://mlsanity.com/paper/2406.05954/) (2024)
- [Self-Exploring Language Models: Active Preference Elicitation for Online Alignment](https://mlsanity.com/paper/2405.19332/) (2024)
- [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://mlsanity.com/paper/2406.00222/) (2024)
- [WPO: Enhancing RLHF with Weighted Preference Optimization](https://mlsanity.com/paper/2406.11827/) (2024)
- [Diverse Preference Optimization](https://mlsanity.com/paper/2501.18101/) (2025)
- [Self-Consistency Preference Optimization](https://mlsanity.com/paper/2411.04109/) (2024)
- [CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs](https://mlsanity.com/paper/2408.10433/) (2024)
- [Discovering Preference Optimization Algorithms with and for Large Language Models](https://mlsanity.com/paper/2406.08414/) (2024)
- [Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferences](https://mlsanity.com/paper/2403.07230/) (2024)

## Abstract (arXiv)

Practitioners commonly align large language models using pairwise preferences, i.e., given labels of the type response A is preferred to response B for a given input. Perhaps less commonly, methods have also been developed for binary feedback, i.e. training models given labels of type response A is good or bad. We show how an existing performant binary feedback method, the Cringe Loss (Adolphs et al., 2022), can be generalized to the pairwise preference setting using a simple soft margin extension. Pairwise Cringe Loss is straightforward to implement and efficient to train, and we find it outperforms state-of-the-art preference optimization algorithms such as PPO and DPO on the AlpacaFarm benchmark. We show that iterations of training of our model are important for improved results, and that we can generalize DPO to Iterative DPO in the same way.