Papers by Tianlong Chen

UQ-Merge: Uncertainty Guided Multimodal Large Language Model Merging (2025.findings-acl)

Challenge:	Bit-flip errors (BFEs) are hardware faults where individual bits in memory or processing units are unintentionally flipped.
Approach:	They propose a novel defense strategy to mitigate bit-flip errors (BFEs) they propose bfe protection and a self-correction mechanism to minimize performance degradation .
Outcome:	The proposed defense strategy minimizes performance degradation while significantly improving robustness against BFEs.

Copied to clipboard

Huaizhi Qu, Xinyu Zhao, Jie Peng, Kwonjoon Lee, Behzad Dariush, Tianlong Chen

Multimodality

Challenge:	Existing models merging methods often lead to suboptimal performance due to harmful models . et al., 2018; 59: 59-64.
Approach:	They propose an uncertainty-guided MLLM merging algorithm that integrates models into a single MLML.
Outcome:	The proposed algorithm improves on held-in and held-out vision-language benchmarks.

SCALE: Towards Collaborative Content Analysis in Social Science with Large Language Model Agents and Human Intervention (2025.acl-long)

Copied to clipboard

Chengshuai Zhao, Zhen Tan, Chau-Wai Wong, Xinyan Zhao, Tianlong Chen, Huan Liu

DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer’s Disease Questions with Scientific Literature (2024.findings-emnlp)

Challenge:	Content analysis is labor-intensive and time-consuming process that requires multiple rounds of manual annotation, domain expert discussion, and rule-based refinement.
Approach:	They propose a multi-agent framework that effectively Simulates Content Analysis via Large language model (LLM) ag Ents.
Outcome:	The proposed framework achieves human-approximated performance across various content analysis tasks.

Copied to clipboard

Dawei Li, Shu Yang, Zhen Tan, Jae Baik, Sukwon Yun, Joseph Lee, Aaron Chacko, Bojian Hou, Duy Duong-Tran, Ying Ding, Huan Liu, Li Shen, Tianlong Chen

Structured Data in NLP

Challenge:	Recent advances in large language models have achieved promising performances across various applications, but the challenge of integrating long-tail knowledge continues to impede the seamless adoption of LLMs in specialized domains.
Approach:	They propose a dynamic co-augmentation framework for the refinement of large language models and knowledge graphs in the context of Alzheimer's Disease.
Outcome:	The proposed framework can be used to study Alzheimer's Disease (AD) using LLMs and KGs.

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction (2026.findings-acl)

Copied to clipboard

Xu Shen, Qi Zhang, Song Wang, Zhen Tan, Xinyu Zhao, Laura Yao, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Kwonjoon Lee, Tianlong Chen

Teaching LLMs to Plan, Not Just Solve: Plan Learning Boosts LLMs Generalization in Reasoning Tasks (2025.findings-emnlp)

Challenge:	Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors.
Approach:	They propose a metacognitive framework that enables step-level error detection and self-correction in Large Language Model based multi-agent systems (MAS) .
Outcome:	The proposed framework outperforms baselines on the Who When benchmark and delivers consistent gains on AgentErrorBench.

Copied to clipboard

Tianlong Wang, Junzhe Chen, Weibin Liao, Xueting Han, Jing Bai

Reasoning

Challenge:	Existing methods for reinforcement learning (RL) on self-generated data are limited in many domains.
Approach:	a new framework combines plan-based search with Step-level Advantage Preference Optimization to optimize plan learning.
Outcome:	The proposed framework improves in-domain performance and out-of-domain benchmarks.

In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents (2025.acl-long)

Copied to clipboard

Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, Anand Rajan Iyer, Tianlong Chen, Huan Liu, Chen-Yu Lee, Tomas Pfister

Natural Language Interfaces

Challenge:	Existing approaches to long-term dialogue memory management fail to capture the natural semantic structure of conversations, leading to fragmented and incomplete representations.
Approach:	They propose a mechanism that integrates forward- and backward-looking reflections into a personalized memory bank for effective future retrieval.
Outcome:	The proposed mechanism outperforms state-of-the-art benchmarks on a long-term dialogue memory model.

FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping (2024.emnlp-main)

Copied to clipboard

Ajay Jaiswal, Bodun Hu, Lu Yin, Yeonju Ro, Tianlong Chen, Shiwei Liu, Aditya Akella

Challenge:	Autoregressive Large Language Models (LLMs) are omnipresent but typically come with a substantial model size.
Approach:	They propose a novel fine-grained skip strategy for autoregressive large language models . they observe the saturation of computationally expensive feed-forward blocks of LLMs .
Outcome:	The proposed method can skip 25-30% of FFN blocks with marginal change in performance on knowledge-intensive generation tasks.

EQA-RM: A Generative Embodied Reward Model with Test-time Scaling (2025.emnlp-main)

Copied to clipboard

Yuhang Chen, Zhen Tan, Tianlong Chen

Challenge:	Existing generic Reward Models are ill-equipped for dynamic and interactive domains.
Approach:	They propose a novel generative multimodal reward model specifically architected for EQA that provides interpretable, structured reward feedback.
Outcome:	The proposed model outperforms proprietary benchmarks, including Gemini-2.5-Flash, GPT-4o, Claude-3.5-Haiku, and open-sourced state-of-the-art models such as RoVRM and VisualPRM.

Dataset and Enhanced Model for Eligibility Criteria-to-SQL Semantic Parsing (2020.lrec-1)

Copied to clipboard

Xiaojing Yu, Tianlong Chen, Zhengjie Yu, Huiyu Li, Yang Yang, Xiaoqian Jiang, Anxiao Jiang

Programming Languages in NLP

Challenge:	Clinical trials require that patients meet eligibility criteria to ensure safety and effectiveness of studies.
Approach:	They propose a dataset that includes the first-of-its-kind eligibility-criteria corpus and queries for criteria-to-sql . they propose 'neuro semantic parser' which can translate eligibility criteria to executable SQL queries .
Outcome:	The proposed parser outperforms existing state-of-the-art general-purpose models while highlighting the challenges presented by the new dataset.

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense (2025.naacl-long)

Copied to clipboard

Yang Ouyang, Hengrui Gu, Shuhang Lin, Wenyue Hua, Jie Peng, Bhavya Kailkhura, Meijun Gao, Tianlong Chen, Kaixiong Zhou

Task-Aware Resolution Optimization for Visual Large Language Models (2025.emnlp-main)

Challenge:	Existing methods to defend against jailbreak attacks exploit vulnerabilities to elicit unintended or harmful outputs.
Approach:	They propose a method to defend against jailbreak attacks by patching specific layers within large language models through self-augmented datasets.
Outcome:	The proposed approach reduces harmfulness and attack success rate of jailbreak attacks without compromising utility for benign queries compared to previous methods.

Copied to clipboard

Weiqing Luo, Zhen Tan, Yifan Li, Xinyu Zhao, Kwonjoon Lee, Behzad Dariush, Tianlong Chen

Visual Data in NLP

Challenge:	Existing visual large language models pre-assume a fixed resolution for downstream tasks, leading to sub-optimal performance.
Approach:	They propose a formula to determine the optimal resolution for a given vision-language task . they then propose 'parameter-efficient' fine-tuning technique to extend the visual input resolution .
Outcome:	The proposed method is based on rigorous experiments on vision-language tasks.

Contextualization Distillation from Large Language Model for Knowledge Graph Completion (2024.findings-eacl)

Copied to clipboard

Dawei Li, Zhen Tan, Tianlong Chen, Huan Liu

BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment (2025.naacl-long)

Challenge:	Existing knowledge graph completion models lack textual information, which limits their performance . a plug-in-and-play approach is needed to train small models in descriptive context .
Approach:	They propose a plug-in-and-play approach to knowledge graph completion that prompts LLMs to generate descriptive context.
Outcome:	The proposed method improves performance on Wikipedia articles and synset definitions.

Copied to clipboard

Sizhe Wang, Yongqi Tong, Hengyuan Zhang, Dawei Li, Xin Zhang, Tianlong Chen

Challenge:	Reinforcement Learning with Human Feedback (RLHF) is the key to the success of large language models (LLMs) in recent years.
Approach:	They propose a method to balance the number of prompts and responses to improve knowledge breadth and knowledge depth by introducing gradient-based clustering to estimate the knowledge informativeness and usefulness of each augmented sample.
Outcome:	The proposed method outperforms baseline methods while maintaining training efficiency.

GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models (2025.findings-acl)

Copied to clipboard

Mufan Qiu, Xinyu Hu, Fengwei Zhan, Sukwon Yun, Jie Peng, Ruichen Zhang, Bhavya Kailkhura, Jiekun Yang, Tianlong Chen

Structured Data in NLP

Challenge:	Foundation models for single-cell RNA sequencing ignore biological prior knowledge encoded in gene regulatory relationships and fail to leverage multi-omics signals.
Approach:	They propose a framework that integrates multi-scale gene regulatory networks into RNA foundation model training.
Outcome:	The proposed framework improves on state-of-the-art models on three downstream tasks . it integrates multi-scale gene regulatory networks (GRNs) from multi-omics data into training .

Learning Flexible Large Multimodal Models with Arbitrary Modality Combinations (2026.findings-acl)

Copied to clipboard

Xinyu Zhao, Kangqi Ni, Jie Peng, Ang Li, Tianlong Chen

Dialogue is Better Than Monologue: Instructing Meidcal LLMs via Strategic Conversations (2026.findings-eacl)

Challenge:	Multimodal Large Language Models (MLLMs) have potential for cross-modal understanding . but extending MLLM to handle diverse modalities introduces two challenges .
Approach:	They propose a dual-stage compression mechanism to reduce the number of modality tokens per modality and condense it into a single, compact token sequence.
Outcome:	Experiments show that Flex-M3 outperforms its counterpart trained on only full-modality data.

Copied to clipboard

Zijie Liu, Xinyu Zhao, Jie Peng, Jinhao Duan, Zhuangdi Zhu, Qingyu Chen, Kaidi Xu, Xia Hu, Tianlong Chen

Natural Language Interfaces

Challenge:	Existing tuning methods for medical AI models are monologue-based . existing benchmarks are based on licensing exams or research articles .
Approach:	They propose a benchmark to expose limitations of monologue-based tuning for medical AI models . they use a large dialogue dataset to capture stepwise diagnostic reasoning .
Outcome:	The proposed model outperforms monologue-tuned models on a medical question answering task and improves accuracy on standard medical QA benchmarks.

Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning (2024.emnlp-main)

Copied to clipboard

Abhinav Bandari, Lu Yin, Cheng-Yu Hsieh, Ajay Jaiswal, Tianlong Chen, Li Shen, Ranjay Krishna, Shiwei Liu

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges (2025.findings-acl)

Challenge:	Existing approaches to prune LLMs rely on the C4 dataset as calibration data . arithmetic datasets perform better than pre-training datasets for pruning, whereas chain-of-thought is only useful on certain tasks.
Approach:	They evaluate the selection of calibration data for LLM pruning across a wide range of datasets . they find that C4 is not the optimal calibration data, and that CoT is only useful on certain tasks.
Outcome:	The chosen calibration data significantly impacts the performance of pruned LLMs, the authors found . their results shed light on the importance of carefully selecting calibration data for LLM pruning .

Copied to clipboard

Tiejin Chen, Pingzhi Li, Kaixiong Zhou, Tianlong Chen, Hua Wei

Multimodality

Challenge:	Privacy risks in text-only Large Language Models are well-documented, especially their tendency to memorize and leak sensitive information.
Approach:	They propose a dataset to assess privacy risks across multi-modal tasks and scenarios . they demonstrate how models leak sensitive data across various tasks .
Outcome:	The proposed model can leak sensitive data embedded in images or stored in memory, exposing privacy risks.

Glue pizza and eat rocks - Exploiting Vulnerabilities in Retrieval-Augmented Generative Models (2024.emnlp-main)

Copied to clipboard

Zhen Tan, Chengshuai Zhao, Raha Moraffah, Yifan Li, Song Wang, Jundong Li, Tianlong Chen, Huan Liu

Vision Language Model Helps Private Information De-Identification in Vision Data (2025.findings-acl)

Challenge:	Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases.
Approach:	They propose to exploit openness of RAG models by injecting deceptive content into the retrieval database, intentionally changing the model’s behavior.
Outcome:	The proposed model can be exploited through crafted content uploads with access to the retriever.

Copied to clipboard

Tiejin Chen, Pingzhi Li, Kaixiong Zhou, Tianlong Chen, Hua Wei

Visual Data in NLP

Challenge:	Visual Language Models (VLMs) have gained popularity due to their ability to solve imagerelated tasks.
Approach:	They propose a framework to enhance privacy awareness of visual language models . they use a specialized instruction-tuning dataset and a tailored training methodology .
Outcome:	The proposed framework outperforms existing approaches in handling private information.

DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models (2023.acl-long)

Copied to clipboard

Xuxi Chen, Tianlong Chen, Weizhu Chen, Ahmed Hassan Awadallah, Zhangyang Wang, Yu Cheng

ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation (2026.findings-acl)

Challenge:	Conventional fine-tuning works through updating all of the parameters in the pre-trained model, but as the size of pre-train models grows, it can be time-consuming and computationally expensive.
Approach:	They propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights.
Outcome:	The proposed framework saves 25% inference FLOPs while maintaining competitive downstream performance.

Copied to clipboard

Yihua Zhang, Mingfu Liang, Jiyan Yang, Rong Jin, Wen-Yen Chen, Yiping Han, Huayu Li, Buyun Zhang, Liang Luo, Luke Simon, Sijia Liu, Tianlong Chen, Xi Liu

Agents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks (2025.acl-long)

Challenge:	Recent advances in multimodal recommenders lack explicit reasoning and self-awareness of uncertainty.
Approach:	They propose a reasoning-augmented multimodal agent structured around a three-stage explicit reasoning pipeline.
Outcome:	The proposed agent improves ranking metrics and performance on four standard recommendation tasks across five real-world datasets.

Copied to clipboard

Rana Shahroz, Zhen Tan, Sukwon Yun, Charles Fleming, Tianlong Chen

SConU: Selective Conformal Uncertainty in Large Language Models (2025.acl-long)

Challenge:	Multi-agent LLMs are prone to adversarial attacks because of constraints such as limited token bandwidth and latency between message delivery.
Approach:	They propose a permutation-invariant adversarial attack that optimizes prompt distribution across latency and bandwidth constraints to bypass distributed safety mechanisms within the system.
Outcome:	The proposed method outperforms conventional attacks by up to 7 on multiple models.

Copied to clipboard

Zhiyuan Wang, Qingni Wang, Yue Zhang, Tianlong Chen, Xiaofeng Zhu, Xiaoshuang Shi, Kaidi Xu

Demystify the Role of Memory in Machine Learning Engineering Agents (2026.findings-acl)

Challenge:	Existing frameworks fail to identify outliers that violate the exchangeability assumption, leading to unbounded miscoverage rates and unactionable prediction sets.
Approach:	They propose a method that implements significance tests to determine whether a given sample deviates from the uncertainty distribution of the calibration set.
Outcome:	The proposed approach facilitates rigorous management of miscoverage rates across single-domain and interdisciplinary contexts, and enhances the efficiency of predictions.

Copied to clipboard

Xinyu Zhao, Junpeng Wang, Yuzhong Chen, Menghai Pan, Chin-Chia Michael Yeh, Jiarui Sun, Yan Zheng, Mahashweta Das, Tianlong Chen

Challenge:	Unlike short, reactive exchanges, MLE agents solve tasks through cycles of experimentation and improvement where past errors can inform future success.
Approach:	They propose a dynamic coding memory that captures and reuses debugging experiences and integrates it into two representative agent paradigms.
Outcome:	The proposed agent model captures and reuses debugging experiences and integrates it into two agent paradigms.

MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models (2025.emnlp-main)

Copied to clipboard

Shrey Pandit, Jiawei Xu, Junyuan Hong, Zhangyang Wang, Tianlong Chen, Kaidi Xu, Ying Ding

Reasoning

Challenge:	Recent advances in Large Language Models (LLMs) generate plausible but factually incorrect outputs, posing serious risks to patient safety and clinical decision-making.
Approach:	They propose a benchmark for medical hallucination detection using 10,000 question-answer pairs derived from PubMedQA.
Outcome:	The proposed model achieves an F1 score as low as 0.625 for detecting 'hard' category hallucinations.

FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference (2025.findings-emnlp)

Copied to clipboard

Dongwei Wang, Zijie Liu, Song Wang, Yuxin Ren, Jianing Deng, Jingtong Hu, Tianlong Chen, Huanrui Yang

Green & Sustainable NLP

Challenge:	Key-Value (KV) cache reading latency increases with context lengths hindering LLM inference . important tokens are sparsely distributed across the long context, making existing retrieval inaccurate .
Approach:	They propose a method to retain a small fraction of KV cache based on token importance . important tokens are often sparsely distributed across the long context .
Outcome:	The proposed method reduces decoding latency by 1.2 to 1.5.

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction (2025.emnlp-main)

Copied to clipboard

Song Wang, Zhen Tan, Zihan Chen, Shuang Zhou, Tianlong Chen, Jundong Li

Multimodality

Challenge:	Existing methods for multi-agent collaboration rely on static or graph-based topologies lacking flexibility and adaptability.
Approach:	They propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure.
Outcome:	The proposed method achieves superior performance while significantly reducing communication overhead.

Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design (2025.naacl-long)

Copied to clipboard

Mohan Zhang, Pingzhi Li, Jie Peng, Mufan Qiu, Tianlong Chen

Green & Sustainable NLP

Challenge:	Using Mixture-of-Experts, researchers have found that efficient MoE is difficult to achieve due to two key reasons: imbalanced expert activation and massive communication overhead.
Approach:	They propose a collaboration-constrained routing strategy that encourages more specialized expert groups and leverages expert specialization.
Outcome:	The proposed approach achieves an average performance improvement of 0.51% and 0.33% on LLaMA-MoE and Qwen-MaE respectively.

ReTA: Recursively Thinking Ahead to Improve the Strategic Reasoning of Large Language Models (2024.naacl-long)

Copied to clipboard

Jinhao Duan, Shiqi Wang, James Diffenderfer, Lichao Sun, Tianlong Chen, Bhavya Kailkhura, Kaidi Xu

Bag of Tricks for Sparse Mixture-of-Experts: A Benchmark Across Reasoning, Efficiency, and Safety (2025.findings-emnlp)

Challenge:	Existing logical reasoning evaluations of Large Language Models (LLMs) focus on single-turn and static environments, such as arithmetic problems.
Approach:	They propose a Recursively Thinking-Ahead agent that analyzes the opponents’ future moves/actions and assigns reward signals for these situations.
Outcome:	The proposed agent is based on two scenarios: Online Racing and Offline Probing.

Copied to clipboard

Mufan Qiu, Zheyu Shen, Pingzhi Li, Ang Li, Tianlong Chen

GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing (2025.naacl-long)

Challenge:	Existing benchmarks focus on isolated aspects of MoE, with conflicting conclusions . a lack of consensus on optimal design choices is limiting to specific aspects of the model.
Approach:	They propose to evaluate two popular MoE backbones across four dimensions of design choices . they find token-level routing and z-loss regularization improve reasoning performance .
Outcome:	The proposed framework evaluates two popular MoE backbones on over eight metrics.

Copied to clipboard

Jinhao Duan, Xinyu Zhao, Zhuoxuan Zhang, Eunhye Grace Ko, Lily Boddy, Chenan Wang, Tianhao Li, Alexander Rasgon, Junyuan Hong, Min Kyung Lee, Chenxi Yuan, Qi Long, Ying Ding, Tianlong Chen, Kaidi Xu

Natural Language Interfaces

Challenge:	Large Language Models (LLMs) have demonstrated their effectiveness in human-guided dialogues, but tasks in the real world are more complex and require greater autonomy from LLMs.
Approach:	They propose to characterize LLM-guided conversation into three fundamental components: Goal Navigation, Context Management, Empathetic Engagement and implement an interviewing environment for the evaluation of LLMs.
Outcome:	The proposed LLM outperforms baseline LLMs in interviewing quality and autobiography generation quality.

Spatial Coordinates as a Cell Language: A Multi-Sentence Framework for Imaging Mass Cytometry Analysis (2025.findings-acl)

Copied to clipboard

Chi-Jane Chen, Yuhang Chen, Sukwon Yun, Natalie Stanley, Tianlong Chen

Challenge:	Existing single-cell LLMs struggle to integrate spatial information into natural language, limiting their ability to capture biological relationships.
Approach:	They propose a framework that integrates both single-cell expression and spatial information into natural language using a multi-sentence approach.
Outcome:	The proposed framework outperforms existing single-cell LLMs on preprocessed IMC datasets for diabetes and brain tumors while improving interpretability.

ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion (2025.findings-emnlp)

Copied to clipboard

Rana Shahroz, Dongwen Tang, Pingzhi Li, Kai Wang, Tianlong Chen