Papers by Meng Gao
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)
Copied to clipboard
Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin
| Challenge: | a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities . |
| Approach: | They present a comparative analysis to identify and distinguish LLM activities from human activities. |
| Outcome: | The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities. |
Aligning Large Language Models with Implicit Preferences from User-Generated Content (2025.acl-long)
Copied to clipboard
Zhaoxuan Tan, Zheng Li, Tianyi Liu, Haodong Wang, Hyokun Yun, Ming Zeng, Pei Chen, Zhihan Zhang, Yifan Gao, Ruijie Wang, Priyanka Nigam, Bing Yin, Meng Jiang
| Challenge: | Existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale. |
| Approach: | They propose a framework that leverages implicit preferences in unlabeled user-generated content to generate preference data. |
| Outcome: | The proposed framework transforms user-generated content into user queries and generates responses from the policy model. |
AdaTooler-V: Adaptive Tool-Use for Images and Videos (2026.findings-acl)
Copied to clipboard
Chaoyang Wang, Kaituo Feng, Dongyang Chen, Zhongyu Wang, Zhixun Li, Sicheng Gao, Meng Meng, Xu Zhou, Manyuan Zhang, Yuzhang Shang, Xiangyu Yue
| Challenge: | Existing models exhibit blind tool-use reasoning patterns, which significantly increases inference overhead and degrades model performance. |
| Approach: | They propose an MLLM that performs adaptive tool-use by determining whether a visual problem truly requires tools. |
| Outcome: | The proposed model outperforms existing methods in visual reasoning tasks. |
Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigm (2024.findings-acl)
Copied to clipboard
| Challenge: | Document-level event extraction aims to extract structured information from unstructured text. |
| Approach: | They propose a cross-document event extraction pipeline that integrates event information from multiple documents and provides a comprehensive perspective on events. |
| Outcome: | The proposed pipeline achieves about 72% F1 in end-to-end cross-document event extraction, setting up a benchmark for future research. |
IHEval: Evaluating Language Models on Following the Instruction Hierarchy (2025.naacl-long)
Copied to clipboard
Zhihan Zhang, Shiyang Li, Zixuan Zhang, Xin Liu, Haoming Jiang, Xianfeng Tang, Yifan Gao, Zheng Li, Haodong Wang, Zhaoxuan Tan, Yichuan Li, Qingyu Yin, Bing Yin, Meng Jiang
| Challenge: | Instruction-tuned language models (LMs) are increasingly deployed as interactive services across various applications. |
| Approach: | They propose a benchmark to evaluate models' ability to follow the instruction hierarchy by comparing their models to a set of benchmarks. |
| Outcome: | The proposed benchmark covers 3,538 examples across nine tasks covering cases where instructions in different priorities either align or conflict. |
TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing adversarial models rely on keyword matching and ignore relevant contextual relations for answer prediction. |
| Approach: | They propose to use keyword matching to attack model with two biases that rely on a perturbed answer sentence and a distracting answer sentence to misguide model. |
| Outcome: | The proposed method produces fluent and grammatical adversarial contexts while maintaining gold answers. |
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. |
SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing issue-resolving frameworks rely on commercial models, leading to high costs and privacy concerns. |
| Approach: | They propose a training approach to enhance issue resolving capability of LLMs by decomposing issue reasolving into subtasks. |
| Outcome: | The proposed approach improves issue-resolving performance and generalizes model . it is cost-effective and provides a cost-efficient alternative to commercial models . |
Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks (2022.acl-short)
Copied to clipboard
| Challenge: | Experimental results show text smoothing outperforms data augmentation methods by a substantial margin. |
| Approach: | They propose to use a masked language model to convert a token to a smoothed representation by converting a sentence from its one-hot representation to 'controllable smoothes' they propose to combine text smoothing with other data augmentation methods to achieve better performance. |
| Outcome: | The proposed method outperforms mainstream data augmentation methods by a substantial margin on different datasets in a low-resource regime. |
GR1: Reinforcement-Enhanced LLM for Geoscience Reasoning (2026.findings-acl)
Copied to clipboard
Yule Xie, Jiaxin Ding, Cheng Deng, Shiqing Gao, Junran Zhang, Sibo Zhang, Zeyuan Wang, Ke Wu, Xin Ding, Luoyi Fu, Meng Jin, Xinbing Wang
| Challenge: | Recent advances in large language models have demonstrated RL's substantial capacity to enhance multi-step reasoning beyond what supervised instruction tuning achieves. |
| Approach: | They propose a framework that converts multimodal questions into descriptive text . they propose RL-enhanced geoscience reasoning that can be fine-tuned to a text-only level . |
| Outcome: | The proposed framework improves accuracy and accuracy on multimodal questions while preserving answerability and difficulty. |
PD3F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work lacks mitigation strategies against resource consumption attacks . existing work does not provide mitigation strategies for real-world LLM deployments . |
| Approach: | They propose a pluggable and dynamic doS-Defense framework which employs a two-stage approach to defend against resource consumption attacks from both the input and output sides. |
| Outcome: | The proposed framework significantly mitigates resource consumption attacks, improving users’ access capacity by up to 500% during adversarial load. |
Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning (2024.findings-naacl)
Copied to clipboard
Tianhua Zhang, Jiaxin Ge, Hongyin Luo, Yung-Sung Chuang, Mingye Gao, Yuan Gong, Yoon Kim, Xixin Wu, Helen Meng, James Glass
| Challenge: | Existing methods for surfacing symbolic reasoning capabilities are limited to narrow tasks . arithmetic computations are unnatural to perform in pure language space, and hence present difficulties for LLMs. |
| Approach: | They propose a natural language embedded program framework for solving symbolic reasoning tasks. |
| Outcome: | The proposed framework improves on strong baselines across math and symbolic reasoning, text classification, question answering, and instruction following tasks. |
Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Fengran Mo, Yifan Gao, Sha Li, Hansi Zeng, Xin Liu, Zhaoxuan Tan, Xian Li, Jianshu Chen, Dakuo Wang, Meng Jiang
| Challenge: | Existing studies focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions. |
| Approach: | They propose a conversational agent that interleaves search and reasoning across turns and provides tailored rewards towards evolving user goals. |
| Outcome: | The proposed agent interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals. |
Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning (2026.acl-long)
Copied to clipboard
Siyuan Gan, Jiaheng Liu, Boyan Wang, Tianpei Yang, Runqing Miao, Yuyao Zhang, Fanyu Meng, Junlan Feng, Linjian Meng, Jing Huo, Yang Gao
| Challenge: | Existing work on large reasoning models (LRMs) focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query. |
| Approach: | They propose to use reinforcement learning to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query. |
| Outcome: | The proposed model reduces token usage by around 50%$ compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5b, while significantly improving accuracy. |
Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Information (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing cross-document event coreference resolution models lack the ability to capture long-distance dependencies. |
| Approach: | They propose to construct document-level Rhetorical Structure Theory trees and cross-document Lexical Chains to model structural and semantic information of documents. |
| Outcome: | The proposed model outperforms baseline models on English and Chinese datasets by large margins. |
Improving Domain Generalization for Prompt-Aware Essay Scoring via Disentangled Representation Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing AES models are either prompt-specific or prompt-adaptive and cannot generalize well on “unseen” prompts. |
| Approach: | They propose a prompt-aware neural AES model to extract comprehensive representation for essay scoring, including both prompt-invariant and prompt-specific features. |
| Outcome: | The proposed model extracts comprehensive representation for essay scoring, including both prompt-invariant and prompt-specific features. |
BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents (2026.acl-long)
Copied to clipboard
Zijian Chen, Xueguang Ma, Shengyao Zhuang, Ping Nie, Kai Zou, Sahel Sharifymoghaddam, Andrew Liu, Joshua Green, Kshama Patel, Ruoxi Meng, Mingyi Su, Yanxi Li, Haoran Hong, Xinyu Shi, Xuye Liu, Hosna Oyarhoseini, Nandan Thakur, Crystina Zhang, Luyu Gao, Wenhu Chen, Jimmy Lin
| Challenge: | Existing benchmarks for deep search agents rely on blackbox web search APIs . dynamic and opaque web APIs hinder reproducibility and fair comparisons - authors . |
| Approach: | They propose a benchmark that employs a fixed corpus for controlled retrieval for deep search agents. |
| Outcome: | The new benchmark shows that agents that combine large language models with retrieval tools excel at complex, reasoning-intensive queries. |
From Discrimination to Generation: Low-Resource Intent Detection with Language Model Instruction Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies fine-tune discriminative models on specific defined intent classes, preventing them from being directly adopted to new intent domains. |
| Approach: | They propose to use a pre-trained generative intent model to detect new intents from different domains with no parameter updates. |
| Outcome: | The proposed model outperforms baselines that need further fine-tuning or domain-specific samples. |
Towards Intrinsic Interpretability of Large Language Models: A Survey of Design Principles and Architectures (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on explainable AI focus on post-hoc explanation methods that interpret trained models through external approximations. |
| Approach: | They propose to categorize existing approaches into five design paradigms: functional transparency, concept alignment, representational decomposability, explicit modularization, and latent sparsity induction. |
| Outcome: | The proposed approaches are categorized into five design paradigms: functional transparency, concept alignment, representational decomposability, explicit modularization, and latent sparsity induction. |
ChartAssistant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Charts are an effective tool for understanding data patterns, but their combination of graphical elements and textual components poses challenges for general-purpose multimodal models. |
| Approach: | They propose a chart-based vision-language model for universal chart comprehension and reasoning that leverages a dataset of chart-related tasks. |
| Outcome: | The proposed model outperforms the state-of-the-art charts with zero-shot setting on various chart tasks. |
Clear Up Confusion: Iterative Differential Generation for Fine-grained Intent Detection with Contrastive Feedback (2025.coling-main)
Copied to clipboard
| Challenge: | Recent studies on fine-grained intent detection have focused on collecting large-scale and high-quality samples via crowdsourcing resulting in data scarcity. |
| Approach: | They propose an iterative differential generation framework with contrastive feedback to generate high-quality pseudo samples and accurately capture the crucial nuances in target class distribution. |
| Outcome: | The proposed framework generates high-quality pseudo samples and captures crucial nuances in target class distribution. |
Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies on keyphrase generation on non-English languages haven’t been vastly investigated. |
| Approach: | They propose a retrieval-augmented method for multilingual keyphrase generation that leverages keyphrase annotations in English datasets to facilitate generating keyphrases in low-resource languages. |
| Outcome: | The proposed model outperforms baselines on non-English keyphrase generation datasets and the proposed model is scalable. |
STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems (2026.acl-long)
Copied to clipboard
| Challenge: | Empathetic dialogue requires not only recognizing a user’s emotional state but also making strategy-aware, context-sensitive decisions throughout response generation. |
| Approach: | They propose a STRategy-grounded, interpretable, and DEep reasoning framework that models Empathetic Dialogue through structured, strategy-conditioned reasoning. |
| Outcome: | The proposed framework outperforms existing methods on automatic metrics and human evaluations. |