Papers by Yixia Li
MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning (2025.naacl-long)
Copied to clipboard
| Challenge: | Efficient finetuning of large language models (LLMs) aims to adapt the LLMs with reduced computational and memory costs. |
| Approach: | They propose a simple yet effective method that initializes low-rank matrices with Gaussian distribution and zero values while keeping the original weight matrics frozen. |
| Outcome: | The proposed approach only updates the minor components of the weight matrix while keeping the principal singular components frozen. |
G2: Guided Generation for Enhanced Output Diversity in LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to enhance output diversity but compromise quality of outputs. |
| Approach: | They propose a training-free plug-and-play method that enhances output diversity while preserving generation quality. |
| Outcome: | The proposed method enhances output diversity while maintaining an optimal balance between diversity and quality. |
From Word to World: Can Large Language Models be Implicit Text-based World Models? (2026.acl-long)
Copied to clipboard
Yixia Li, Hongru Wang, Jiahao Qiu, Zhenfei Yin, Dongdong Zhang, Cheng Qian, Zeping Li, Xiaoteng Ma, Guanhua Chen, Heng Ji
| Challenge: | Agentic learning increasingly hinges on interaction, yet real-world experience is expensive, limited, and often irreversible at inference time. |
| Approach: | They propose a framework that reframes language modeling as next-state prediction under interaction. |
| Outcome: | The proposed framework evaluates world models in text-based environments . it shows that sufficiently trained models capture coherent environment dynamics . |
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Recent approaches to reduce resource requirements for task-specific large language models have been developed. |
| Approach: | They propose a delta compression approach that optimizes for importance of a model . they use SVD to dynamically adjust the sparsity ratios of different vectors based on their importance . |
| Outcome: | The proposed approach achieves state-of-the-art in retaining task-specific knowledge even at high sparsity ratios. |
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks (2026.acl-long)
Copied to clipboard
Tianyi Wang, Yixia Li, Long Li, Yibiao Chen, Shaohan Huang, Yun Chen, Peng Li, Yang Liu, Guanhua Chen
| Challenge: | Proximal Policy Optimization (PPO) is central to aligning Large Language Models with verifiable rewards. |
| Approach: | They propose a scalable algorithm that harmonizes sample efficiency with stability of outcome-based updates. |
| Outcome: | The proposed algorithm outperforms standard PPO and matches the performance of computation-heavy group-based methods. |
Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents (2026.acl-long)
Copied to clipboard
Zeping Li, Hongru Wang, Yiwen Zhao, Guanhua Chen, Yixia Li, Keyang Chen, Yixin Cao, Guangnan Ye, Hongfeng Chai, Zhenfei Yin
| Challenge: | Large language models excel in mathematical reasoning and multi-hop question answering tasks, but in long trajectories, agents often invoke tools excessively or inappropriately, increasing computation cost and derailing the reasoning process. |
| Approach: | They propose to use entropy reduction as a supervisory signal to reduce tool calls . they propose to design two reward strategies to address the needs of optimizing tool-use behavior. |
| Outcome: | The proposed reward strategies reduce tool calls by 72.07% and improve performance by 22.27%. |
No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning (2026.acl-long)
Copied to clipboard
Zhicong Li, Lingjie Jiang, Yulan Hu, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen, Zheng Pan, Xin Li, Yong Liu
| Challenge: | Current methods for training Large Language Model agents rely on static or offline critic models, which fail to adapt as the policy evolves. |
| Approach: | They propose a framework that integrates a critique and a policy to optimize the policy and critic through a synchronized co-evolutionary loop. |
| Outcome: | The proposed framework yields more stable training and higher long-horizon task success across open-world environments. |
VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation (2026.acl-long)
Copied to clipboard
Yixia Li, Yaqing Shi, Zhiwen Ruan, Dongdong Zhang, Lingjie Jiang, Shaohan Huang, Yun Chen, Guanhua Chen, Furu Wei
| Challenge: | Multimodal large language models have advanced rapidly, yet most remain English-centric . scaling multilingual multimodal instruction tuning is limited by the scarcity and high cost of non-English image–text supervision. |
| Approach: | They propose a framework that decouples multilingual language enhancement from visual alignment by composing complementary task vectors over a shared LLM backbone. |
| Outcome: | The proposed framework achieves competitive performance with a fully multimodally trained model using less than 2% of the text data. |
FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies explore approaches to synthesize instruction data with open-sourced LLMs but require high-quality human-crafted seed data. |
| Approach: | They propose an end-to-end framework to synthesize high-quality instruction data with open-sourced LLMs and sampled unlabeled documents, eliminating the need for seed data. |
| Outcome: | The proposed framework synthesizes high-quality instruction data with open-sourced LLMs and sampled unlabeled documents, eliminating the need for seed data. |
PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | In-context instruction tuning is a method that fine tunes with supervised instruction data to enhance the instruction following ability of large language models. |
| Approach: | They propose an in-context instruction tuning method that incorporates positive and negative examples into the prompt for better performance. |
| Outcome: | The proposed method outperforms baseline instruction tuning methods on in-domain and out-domain tasks up to 9.16 and 3.14 average ROUGE-L scores. |
LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are pretrained on multilingual corpora but exhibit suboptimal performance on low-resource languages. |
| Approach: | They propose a framework that integrates representations from all encoder layers and an adaptive fusion-enhanced attention mechanism to enable layer-wise interaction between the LLM and the multilingual encoder. |
| Outcome: | Experiments on multilingual reasoning tasks show that the proposed framework outperforms baselines. |