Learning Preference Model for LLMs via Automatic Preference Data Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing training methods for large language models rely on human-annotated data. |
| Approach: | They propose to learn the preference model for LLMs via automatic preference data generation (AutoPM) using HHH-guided preference data, they show reliability and potential . |
| Outcome: | The proposed approach enables LLMs to learn human preferences and align with human values. |
Similar Papers
RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs (2024.emnlp-main)
Copied to clipboard
| Challenge: | Preference optimization is a widely adopted post-training technique to align large language models with human preferences. |
| Approach: | They propose a method for generating multilingual feedback data to balance data coverage. |
| Outcome: | The proposed method achieves 54.4% win-rate against current state-of-the-art multilingual LLM in its parameter class and 69.5% win- rate or higher against widely used models like Gemma, Mistral and Llama 3. |
Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment (2025.coling-main)
Copied to clipboard
| Challenge: | Human values are inherently diverse, making it insufficient to align LLMs solely with general preferences. |
| Approach: | They propose a flexible paradigm for individual preference alignment that disentangles preference representation from text generation in LLMs. |
| Outcome: | The proposed method produces aligned quality and better than PEFT-based methods while reducing training time for each new individual preference by 80% to 90%. |
Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that acquiring human preferences by comparing generations is not effective for large language models. |
| Approach: | They propose a preference optimization objective that elicits preferences jointly over the instruction-response pairs. |
| Outcome: | The proposed approach outperforms prior preference optimizations by 5.2% and 3.3% in summarization and open-ended dialogue datasets. |
From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Current approaches to align large language models assume uniform human preferences, overlooking the diversity inherent in human populations. |
| Approach: | They propose a framework for scalable personalized alignment of large language models . they establish a preference space characterizing psychological and behavioral dimensions . |
| Outcome: | The proposed framework improves on existing methods with an average of 17.06% accuracy gain across four benchmarks and a strong adaptation capability to novel preferences. |
Comparison-based Active Preference Learning for Multi-dimensional Personalization (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models have shown remarkable success, but aligning them with human preferences remains a core challenge. |
| Approach: | They propose to capture implicit user preferences from comparative feedback to improve model performance. |
| Outcome: | The proposed framework is able to capture implicit user preferences from comparative feedback. |
Aligning LLMs with Individual Preferences via Interaction (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on LLMs alignment focus on generalizing their behavior to generalized values such as helpfulness, harmlessness, and honesty. |
| Approach: | They train large language models to "interact to align" to implicitly infer user preferences . they use a multi-turn preference dataset to generate a personalized alignment . |
| Outcome: | The proposed method enables dynamic, personalized alignment via interaction with a multi-turn preference dataset. |
Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings (2025.naacl-industry)
Copied to clipboard
Xuanqing Liu, Luyang Kong, Wei Niu, Afshin Khashei, Belinda Zeng, Steve Johnson, Jon Jay, Davor Golac, Matt Pope
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. |
| Approach: | They propose a framework that combines the scalability of LLM-generated labels with the precision of human annotations to achieve higher speed and accuracy comparable to larger models. |
| Outcome: | The proposed framework significantly improves accuracy across utterance-level dialogue tasks, including sentiment detection (over 2%), dialogue act classification (over 1.5%), etc. |
Dissecting Human and LLM Preferences (2024.acl-long)
Copied to clipboard
| Challenge: | a recent study shows that human and Large Language Model preferences are important for model fine-tuning and evaluation. |
| Approach: | They dissect the preferences of human and 32 different Large Language Models to understand their quantitative composition. |
| Outcome: | The proposed model is compared with 32 different large language models using real-world user-model conversations. |
Improving Attributed Text Generation of Large Language Models via Preference Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models have been widely adopted in natural language processing, yet they produce unreliable content. |
| Approach: | They propose to model the attribution task as preference learning and introduce an automatic preference optimization framework that synthesizes attribution preference data. |
| Outcome: | The proposed method achieves state-of-the-art citation F1 with higher answer quality than existing methods. |
Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models have shown excellent performance on knowledge-intensive tasks, but pretraining data tends to contain misleading and conflicting information. |
| Approach: | They systematically analyze LLMs’ learning preferences for data with conflicting knowledge. |
| Outcome: | The proposed model outperforms human-level models on knowledge-intensive tasks by analyzing pretraining data. |