# PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization

arXiv: https://arxiv.org/abs/2608.30597 · HTML: https://mlsanity.com/paper/2608.30597/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [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)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [UltraFeedback: Boosting Language Models with Scaled AI Feedback](https://mlsanity.com/paper/2310.01377/) (2023)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [Statistical Rejection Sampling Improves Preference Optimization](https://mlsanity.com/paper/2309.06657/) (2023)
- [KTO: Model Alignment as Prospect Theoretic Optimization](https://mlsanity.com/paper/2402.01306/) (2024)
- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy](https://mlsanity.com/paper/2507.01352/) (2025)
- [Provably Robust DPO: Aligning Language Models with Noisy Feedback](https://mlsanity.com/paper/2403.00409/) (2024)
- [Diverging Preferences: When do Annotators Disagree and do Models Know?](https://mlsanity.com/paper/2410.14632/) (2024)
- [Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples](https://mlsanity.com/paper/2502.09650/) (2025)
- [Robust Preference Optimization via Dynamic Target Margins](https://mlsanity.com/paper/2506.03690/) (2025)
- [ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference](https://mlsanity.com/paper/2312.02554/) (2023)
- [RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment](https://mlsanity.com/paper/2509.24159/) (2025)

## Abstract (arXiv)

Direct Preference Optimization (DPO) simplifies alignment through pairwise comparisons but assumes all observed preferences are reliable. Real data often violates this assumption, leading to reversed, weak, or ambiguous labels that cause harmful policy updates. To address this, we propose Posterior Label Correction DPO (PLC-DPO) to robustly optimize preferences by routing each pair's training signal as a clean, flip, or tie case. The key idea is to use the calibrated policy-reference margin as online evidence to take appropriate correction actions. This reframes noisy preference learning as actively correcting supervision direction and strength rather than merely filtering suspicious examples. Across 57 dataset-model-benchmark cells, PLC-DPO obtains the best mean win rate against DPO (60.5 vs. 55.5 for the next-best method). Injected-noise and tie stress tests, human disagreement analysis, and self-confirmation diagnostics further show that the routing remains stable and distinguishes flipped from weakly directional pairs.