Papers by Yanmeng Wang
Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching (2025.findings-acl)
Copied to clipboard
| Challenge: | In-Context Learning (ICL) empowers Large Language Models for rapid task adaptation without fine-tuning. |
| Approach: | They propose a method that aligns fine-tuning gradients between entire training set and selected examples to enable in-context learning and fine-uning. |
| Outcome: | The proposed method outperforms random selection on large LLMs from 4-shot to 128-shot scenarios across 9 datasets. |
ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents (2025.acl-long)
Copied to clipboard
Zhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao, Tianhao Shen, Minghui Zhang, Linxi Su, Shang Wu, Yihang Wu, YuQian Wang, Ye Wang, Wei Hu, Jianfeng Li, Shaojun Wang, Jing Xiao, Deyi Xiong
| Challenge: | Existing models that use Large Language Models (LLMs) show superior performance in various tasks, but lack of controllability leads to unfocused conversations or task failure. |
| Approach: | They propose a standard operating procedure (SOP) framework to regulate dialogue flow by integrating Chain of Thought reasoning and supervised fine-tuning for SOP prediction. |
| Outcome: | The proposed method achieves a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also shows notable gains for open-source models. |
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%. |
Learning to Adapt to Low-Resource Paraphrase Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Conventional approaches to paraphrase generation often rely on a large number of parallel paraphrases, which require a lot of domain knowledge. |
| Approach: | They propose an adapter for paraphrase generation models optimized by meta-learning to overcome domain shifting problem when training on scarce labeled data. |
| Outcome: | The proposed model achieves state-of-the-art on three benchmark datasets. |
Astra: Activation-Space Tail-Eigenvector Low-Rank Adaptation of Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pre-trained models are limited due to suboptimal activation subspaces. |
| Approach: | They propose a method that leverages tail eigenvectors of model output activations to construct low-rank adapters. |
| Outcome: | The proposed method outperforms existing methods across 16 benchmarks and surpasses full fine-tuning in certain scenarios. |
Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to solve question answering (QA) problems are limited by the need for text generation and answer retrieval. |
| Approach: | They propose to introduce QA interaction features in scoring function but at the cost of low efficiency in inference stage. |
| Outcome: | The proposed framework significantly outperforms the state-of-the-art method on multiple answer retrieval datasets. |