# ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks

arXiv: https://arxiv.org/abs/2605.17458 · HTML: https://mlsanity.com/paper/2605.17458/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 30 of its 50 references that are in the map.
- First posted on arXiv 17 May 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://mlsanity.com/paper/1909.03496/) (2019)
- [A Survey on Text Classification: From Shallow to Deep Learning](https://mlsanity.com/paper/2008.00364/) (2020)
- [Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree](https://mlsanity.com/paper/2002.08653/) (2020)
- [Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback](https://mlsanity.com/paper/2108.05382/) (2021)
- [Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Driving](https://mlsanity.com/paper/2109.12516/) (2021)
- [Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation](https://mlsanity.com/paper/2310.02368/) (2023)
- [A Survey on Progress in LLM Alignment from the Perspective of Reward Design](https://mlsanity.com/paper/2505.02666/) (2025)
- [AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations](https://mlsanity.com/paper/2406.18346/) (2024)
- [Towards Reward Fairness in RLHF: From a Resource Allocation Perspective](https://mlsanity.com/paper/2505.23349/) (2025)
- [Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels](https://mlsanity.com/paper/2509.16596/) (2025)
- [Mitigating Class Boundary Label Uncertainty to Reduce Both Model Bias and Variance](https://mlsanity.com/paper/2002.09963/) (2020)
- [Rank over Class: The Untapped Potential of Ranking in Natural Language Processing](https://mlsanity.com/paper/2009.05160/) (2020)
- [Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning](https://mlsanity.com/paper/2306.04925/) (2023)

## Abstract (arXiv)

Text classification models are typically trained via supervised fine-tuning (SFT). However, SFT essentially performs behavior cloning from instance-wise labels and thus fails to adequately capture relative preference relations among samples, which limits the model's ability to shape decision boundaries and calibrate predictive confidence. In this paper, we propose ClaHF, a human feedback-inspired reinforcement learning (RL) framework for text classification that integrates preference modeling and RL optimization into the classification pipeline without requiring additional human annotations. Unlike prior work that relies solely on instance-wise supervision, ClaHF constructs multiple candidate predictions together with their relative ranking relations, and jointly models the Top-1 preference and the ordering among non-optimal candidates within a reward model (RM). This design converts conventional label supervision into preference signals that are directly applicable to policy optimization. We conduct systematic evaluations on eight classification tasks spanning three categories of scenarios. Results demonstrate that ClaHF consistently improves both classification performance and confidence calibration across diverse language models (LMs). The data and code are available at https://anonymous.4open.science/r/ClaHF.