Papers by Justin Chen
Diffusion Guided Language Modeling (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing guidance methods for text generation are prone to decoding errors and degrade performance. |
| Approach: | They propose a model that steers an auto-regressive language model to generate text with desired properties. |
| Outcome: | The proposed model outperforms existing guidance methods on a wide range of benchmark data sets. |
DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning (2026.eacl-long)
Copied to clipboard
Nithin Sivakumaran, Justin Chen, David Wan, Yue Zhang, Jaehong Yoon, Elias Stengel-Eskin, Mohit Bansal
| Challenge: | a key strength of human intelligence is the ability to debate and discuss reasoning with others. |
| Approach: | They propose a multi-agent framework that uses disagreements between visual agents to identify useful visual tools that can resolve inter-agency disagreement. |
| Outcome: | The proposed framework beats the strongest baseline on A-OKVQA and MMMU, respectively. |
GREEN: Generative Radiology Report Evaluation and Error Notation (2024.findings-emnlp)
Copied to clipboard
Sophie Ostmeier, Justin Xu, Zhihong Chen, Maya Varma, Louis Blankemeier, Christian Bluethgen, Arne Md, Michael Moseley, Curtis Langlotz, Akshay Chaudhari, Jean-Benoit Delbrouck
| Challenge: | Existing automated evaluation metrics fail to consider factual correctness or are limited in their interpretability. |
| Approach: | They propose a radiology report evaluation metric that leverages natural language understanding of language models to identify and explain clinically significant errors. |
| Outcome: | The proposed method demonstrates higher correlation with expert error counts and higher alignment with expert preferences when compared to previous methods. |
Reverse Thinking Makes LLMs Stronger Reasoners (2025.naacl-long)
Copied to clipboard
Justin Chen, Zifeng Wang, Hamid Palangi, Rujun Han, Sayna Ebrahimi, Long Le, Vincent Perot, Swaroop Mishra, Mohit Bansal, Chen-Yu Lee, Tomas Pfister
| Challenge: | Reverse-Enhanced Thinking (RevThink) is a framework for large language models to perform reverse thinking. |
| Approach: | They propose a framework for enhancing forward-backward reasoning by collecting data from a teacher model and employing three objectives to train a student model in a multi-task learning fashion. |
| Outcome: | The proposed framework outperforms a fine-tuning method trained on 10x more forward reasoning on 12 datasets covering commonsense, math, and logical reasoning. |
PRInTS: Reward Modeling for Long-Horizon Information Seeking (2026.acl-long)
Copied to clipboard
| Challenge: | Existing PRMs cannot capture richer dimensions of information-seeking steps, such as tool interactions and reasoning over tool outputs. |
| Approach: | They propose a generative PRM trained with dual capabilities that compresses the growing context while preserving essential information for step evaluation. |
| Outcome: | PRInTS improves on FRAMES, GAIA, and WebWalkerQA models while preserving essential information for step evaluation. |
Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection (2026.acl-long)
Copied to clipboard
Tianyi Niu, Justin Chen, Genta Indra Winata, Shi-Xiong Zhang, Supriyo Chakraborty, Sambit Sahu, Yue Zhang, Elias Stengel-Eskin, Mohit Bansal
| Challenge: | Existing approaches typically assume access to ground-truth labeled data . Existing methods require a classifier to select models given an input . |
| Approach: | They propose a routing setting where routers are trained exclusively on generated queries and answers from LLMs. |
| Outcome: | The proposed router outperforms the best query-answer router by 4.6% absolute accuracy when trained on weak generator data. |
ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) still struggle with natural language reasoning tasks. |
| Approach: | They propose a multi-model multi-agent framework that enhances collaborative reasoning between LLM agents via multiple rounds of discussion. |
| Outcome: | Experiments on seven benchmarks show that ReConcile significantly improves LLM reasoning on individual and team levels. |
Automated Structured Radiology Report Generation (2025.acl-long)
Copied to clipboard
Jean-Benoit Delbrouck, Justin Xu, Johannes Moll, Alois Thomas, Zhihong Chen, Sophie Ostmeier, Asfandyar Azhar, Kelvin Zhenghao Li, Andrew Johnston, Christian Bluethgen, Eduardo Pontes Reis, Mohamed S Muneer, Maya Varma, Curtis Langlotz
| Challenge: | Existing models struggle to produce consistent, clinically meaningful reports and standard evaluation metrics fail to capture the nuances of radiological interpretation. |
| Approach: | They propose to reformulate free-text radiology reports into a standardized format, ensuring clarity, consistency, and structured clinical reporting. |
| Outcome: | The proposed task reformulates free-text radiology reports into a standardized format, ensuring clarity, consistency, and structured clinical reporting. |
MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration (2025.naacl-long)
Copied to clipboard
| Challenge: | Multi-agent collaboration among models has shown promise in reasoning tasks but is underexplored in long-form generation tasks like summarization and question-answering. |
| Approach: | They propose a multi-agent multi-model reasoning recipe to improve faithfulness through refinement. |
| Outcome: | The proposed method improves faithfulness and error detection on three summarization datasets and on long-form question-answering tasks. |
Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidance (2025.emnlp-main)
Copied to clipboard
Yilun Liu, Minggui He, Feiyu Yao, Yuhe Ji, Shimin Tao, Jingzhou Du, Justin Li, Jian Gao, Zhang Li, Hao Yang, Boxing Chen, Osamu Yoshie
| Challenge: | Existing solutions for text-to-image synthesis are sensitive on textual prompts, posing a challenge for novice users. |
| Approach: | They propose a dialogue-based TIS prompt generation model that emphasizes user experience for novice users. |
| Outcome: | The proposed model emphasizes user experience for novice users . it improves user-centricity score while maintaining a competitive quality of synthesized images. |
MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Excessive refinement can cause over-correction and reduce performance, authors say . they say MAgICoRe is a framework for multi-agent iteration for coarse-to-fine refinement . |
| Approach: | They propose a framework for multi-agent iteration for coarse-to-fine refinement that reduces excessive refinement by categorizing problems as easy or hard. |
| Outcome: | The proposed framework beats Self-Consistency by 3.4%, Best-of-k by 3.2%, and Self-Refine by 4.0% on Llama-3-8B and GPT- 3.5. |
CheXalign: Preference fine-tuning in chest X-ray interpretation models without human feedback (2025.acl-long)
Copied to clipboard
Dennis Hein, Zhihong Chen, Sophie Ostmeier, Justin Xu, Maya Varma, Eduardo Pontes Reis, Arne Edward Michalson Md, Christian Bluethgen, Hyun Joo Shin, Curtis Langlotz, Akshay S Chaudhari
| Challenge: | Radiologists are a crucial role in translating medical images into actionable reports . however, the field faces staffing shortages and increasing workloads . |
| Approach: | They propose an automated pipeline for preference feedback focusing on chest X-ray radiology report generation (RRG) method leverages publicly available datasets containing pairs of images and radiologist-written reference reports with reference-based metrics, or Judges. |
| Outcome: | The proposed pipeline achieves state-of-the-art CheXbert scores on the MIMIC-CXR dataset while on average maintaining robust performance across six additional image perception and reasoning tasks. |
Location-Aware Visual Question Generation with Lightweight Models (2023.emnlp-main)
Copied to clipboard
Nicholas Suwono, Justin Chen, Tun Hung, Ting-Hao Huang, I-Bin Liao, Yung-Hui Li, Lun-Wei Ku, Shao-Hua Sun
| Challenge: | a novel task aims to generate engaging questions from location-aware information . a lightweight model can be used to generate such questions . |
| Approach: | They propose a task to generate engaging questions from location-aware data . they represent location-based information with surrounding images and a GPS coordinate . |
| Outcome: | The proposed method outperforms baselines regarding human evaluation and evaluation metrics. |
LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization (2026.findings-acl)
Copied to clipboard
Yuanchen Wu, Saurabh Verma, Justin Lee, Fangzhou Xiong, Poppy Zhang, Amel Awadelkarim, Xu Chen, Yubai Yuan, Shawndra Hill
| Challenge: | Large language models (LLMs) are highly sensitive to prompts, but most automatic prompt optimization methods assume access to ground-truth references that are costly to obtain. |
| Approach: | They propose a sample-efficient framework for label-free prompt optimization based on pairwise preference feedback from an LLM judge. |
| Outcome: | Experiments on BIG-bench Hard and MS MARCO show that the proposed framework identifies stronger prompts than label-free baselines while offering favorable quality–cost trade-offs. |
Symbolic Planning and Code Generation for Grounded Dialogue (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models excel at processing and generating text and code, but lack a grounded task-oriented dialogue system that can handle grounding. |
| Approach: | They propose a modular and interpretable grounded dialogue system that integrates a reader and planner to convert partner utterances into executable code and a symbolic planner to determine the next appropriate response. |
| Outcome: | The proposed system outperforms the existing state-of-the-art on a one-common dialogue task and improves task success in human evaluations from 56% to 69% in the most challenging setting. |