| Challenge: | Pre-trained large-scale language models often generate biased or toxic text, misaligning with human intentions. |
| Approach: | They propose to use human feedback to improve LLM alignment by fine-grained token supervision . they ask annotators to edit less preferred responses to make them more favorable . |
| Outcome: | The proposed method improves LLM alignment by up to 5.1% in terms of win rate compared with the traditional model. |
Similar Papers
Don’t Forget Your Reward Values: Language Model Alignment via Value-based Calibration (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for generating large language models have been criticized for their complexity and instability. |
| Approach: | They propose a value-based calibration method to better align Large Language Models with human preferences. |
| Outcome: | The proposed method surpasses existing methods on AI assistant and summarization datasets, providing impressive generalizability, robustness, and diversity in different settings. |
Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Instruction-fine-tuned large language models (LLMs) under 14B parameters underperform on NLU tasks . we explore a framework to improve the NLU capabilities of LLMs . |
| Approach: | They propose to use Proximal Policy Optimization to improve NLU capabilities . they frame NLU as a reinforcement learning environment and optimize for reward signals . |
| Outcome: | The proposed framework outperforms supervised fine-tuning on GLUE and superGLUE tasks. |
AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for LLM alignment optimize tokens using a sparse, response-level reward or preference annotation. |
| Approach: | They propose an RLHF-equivalent distillation method for token-level reward optimization that incorporates the reward learned by DPO into the RLHG objective and builds a token-based teacher distribution. |
| Outcome: | The proposed method bridges the accuracy gap between the reward from the DPO model and the pure reward model by building a contrastive DPO reward with a normal and a reverse DPO. |
Aligning Large Language Models through Synthetic Feedback (2023.emnlp-main)
Copied to clipboard
| Challenge: | Currently, alignment learning requires significant human demonstrations and feedback from proprietary LLMs such as ChatGPT. |
| Approach: | They propose a framework that uses synthetic feedback to align large language models to human values without extensive human annotations and proprietary LLMs. |
| Outcome: | The proposed model outperforms open-source models on human-annotated demonstrations in alignment benchmarks. |
Aligning Large Language Models with Human Preferences through Representation Engineering (2024.acl-long)
Copied to clipboard
Wenhao Liu, Xiaohua Wang, Muling Wu, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Existing methods for achieving this alignment involve employing reinforcement learning from human feedback (RLHF) Existing approaches involve using RLHF to fine-tune LLMs based on human labels . however, RLRF is susceptible to instability during fine- tuning and presents challenges in implementation. |
| Approach: | They propose to use reinforcement learning from human feedback to fine-tune large language models with human preferences to achieve precise control of model behavior. |
| Outcome: | Experiments show that RAHF can be used to capture and manipulate representations to align with a broad spectrum of human preferences or values rather than being confined to a single concept or function. |
Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing reinforcement learning methods do not provide fine-grained supervision for complex reasoning tasks. |
| Approach: | They propose a reinforcement learning method that incorporates a generative model as the reward model and a token-level supervision model for RL training. |
| Outcome: | Experiments on 8 tasks show the proposed method is effective . |
Aligning Large Language Models for Controllable Recommendations (2024.acl-long)
Copied to clipboard
| Challenge: | Existing literature focuses on integrating domain-specific knowledge into LLMs to enhance accuracy using a fixed task template. |
| Approach: | They propose a collection of supervised learning tasks augmented with labels derived from a conventional recommender model to improve LLMs’ proficiency in adhering to recommendation-specific instructions. |
| Outcome: | The proposed approach significantly improves the capability of LLMs to respond to instructions within recommender systems, reducing formatting errors while maintaining a high level of accuracy. |
A Survey on Training-free Alignment of Large Language Models (2025.findings-emnlp)
Copied to clipboard
Birong Pan, Yongqi Li, Weiyu Zhang, Wenpeng Lu, Mayi Xu, Shen Zhou, Yuanyuan Zhu, Ming Zhong, Tieyun Qian
| Challenge: | a survey of large language models (LLMs) aims to ensure outputs adhere to human values, ethical standards, and legal norms. |
| Approach: | They present the first systematic review of TF alignment methods . they categorize them by stages of pre-decoding, in-decoder and post-decoration . |
| Outcome: | The proposed methods are based on training-free (TF) alignment techniques . they are able to be used in open-source and closed-source environments without retraining . |
Aligning Large Language Models via Fully Self-Synthetic Data (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to reinforcement learning from human feedback (RLHF) require expensive human-annotated datasets and proprietary models like GPT-4 to annotate preference pairs. |
| Approach: | They propose a self-synthetic framework for LLM alignment where all training data, including prompts (i.e., user queries), responses, and preferences, are generated by the model itself. |
| Outcome: | The proposed framework enhances the model’s chat capabilities on standard benchmarks like AlpacaEval 2.0 while maintaining strong performance on downstream objective tasks. |
Improving the Robustness of Large Language Models via Consistency Alignment (2024.lrec-main)
Copied to clipboard
Yukun Zhao, Lingyong Yan, Weiwei Sun, Guoliang Xing, Shuaiqiang Wang, Chong Meng, Zhicong Cheng, Zhaochun Ren, Dawei Yin
| Challenge: | Large language models have shown tremendous success in following user instructions and generating helpful responses, but their robustness is still far from optimal. |
| Approach: | They propose a two-stage training framework that helps a model generalize on following instructions via similar instruction augmentations. |
| Outcome: | The proposed training framework improves diversity and aligns the model with human expectations by differentiating subtle differences in similar responses. |