Papers by Chuan Meng
UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations (2025.acl-long)
Copied to clipboard
Fengran Mo, Yifan Gao, Chuan Meng, Xin Liu, Zhuofeng Wu, Kelong Mao, Zhengyang Wang, Pei Chen, Zheng Li, Xian Li, Bing Yin, Meng Jiang
| Challenge: | Existing conversational search systems are usually built with two different models . this separation restricts the system from leveraging the model's intrinsic knowledge simultaneously . Existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses. |
| Approach: | They propose to unify dense retrieval and response generation for large language models in conversation by fine-tuning and mitigating data discrepancy. |
| Outcome: | The proposed model can outperform existing models on five conversational search datasets and reduce inconsistency risks while mitigating data discrepancy. |
MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing (2026.acl-demo)
Copied to clipboard
| Challenge: | Large language model-based multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration. |
| Approach: | They propose a graph-centric framework for orchestrating large language model-based multi-agent systems . they compile a user's natural-language intent into an editable workflow specification and then into an executable graph . |
| Outcome: | The proposed framework compiles natural-language intent into an executable graph and then compile and executes it at runtime. |
Unveiling Multimodal Processing: Exploring Activation Patterns in Multimodal LLMs for Interpretability and Efficiency (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in multimodal large language models have remained opaque. |
| Approach: | They propose a method to convert dense MLLMs into fine-grained Mixture-of-Experts architectures. |
| Outcome: | The proposed method outperforms random expert pruning and sparse activation and model pruning. |
Expand, Highlight, Generate: RL-driven Document Generation for Passage Reranking (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies use large language models to generate training data for ranking models. |
| Approach: | They propose a pipeline that generates synthetic documents from queries using large language models . they propose RL-based reinforcement learning to optimize the pipeline . |
| Outcome: | The proposed pipeline outperforms existing state-of-the-art methods in generating synthetic documents more effectively. |
SOLID: Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking Dialogs (2025.findings-naacl)
Copied to clipboard
Arian Askari, Roxana Petcu, Chuan Meng, Mohammad Aliannejadi, Amin Abolghasemi, Evangelos Kanoulas, Suzan Verberne
| Challenge: | Existing methods for intent prediction rely on human feedback and are tailored to structured intents. |
| Approach: | They propose a method that generates dialogs turn-by-turn using self-seeding and multi-intent self-instructing strategies. |
| Outcome: | The proposed methods generate dialogs turn-by-turn using self-seeding and multi-intent self-instructing strategies. |