Papers by Justin Lee
A Neural Pairwise Ranking Model for Readability Assessment (2022.findings-acl)
Copied to clipboard
| Challenge: | Automatic Readability Assessment (ARA) is traditionally treated as a classification problem in NLP research. |
| Approach: | They propose a neural ranking approach to automatic readability assessment (ARA) they propose 'neural' ranking methods that can be used to rank texts by reading level . |
| Outcome: | The proposed approach performs well in monolingual single/cross corpus testing scenarios and achieves a zero-shot cross-lingual ranking accuracy of over 80% for both French and Spanish when trained on English data. |
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. |
Methods, Applications, and Directions of Learning-to-Rank in NLP Research (2024.findings-naacl)
Copied to clipboard
| Challenge: | Learning-to-rank (LTR) algorithms aim to order items according to some criteria. |
| Approach: | They focus on the formal background of LTR and the most widely-used supervised methods . they also discuss how large language models are changing the LTR landscape . |
| Outcome: | The proposed methods are used in natural language processing and information retrieval tasks. |
Dynamic Meta-Metrics: Source-Sentence Conditioned Weighting for MT Evaluation (2026.acl-srw)
Copied to clipboard
| Challenge: | Rather than relying on a single static ensemble or language-specific weighting, DMM adapts the metric combination based on properties of the source segment. |
| Approach: | They propose a framework for machine translation evaluation that learns source-sentence conditioned combinations of existing metrics. |
| Outcome: | The proposed framework outperforms linear and Gaussian process-based ensembles across multiple language pairs and introducing soft conditioning yields gains over linear models. |
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. |