Papers by David Sun
FOLIO: Natural Language Reasoning with First-Order Logic (2024.emnlp-main)
Copied to clipboard
Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Wenfei Zhou, James Coady, David Peng, Yujie Qiao, Luke Benson, Lucy Sun, Alexander Wardle-Solano, Hannah Szabó, Ekaterina Zubova, Matthew Burtell, Jonathan Fan, Yixin Liu, Brian Wong, Malcolm Sailor, Ansong Ni, Linyong Nan, Jungo Kasai, Tao Yu, Rui Zhang, Alexander Fabbri, Wojciech Kryscinski, Semih Yavuz, Ye Liu, Xi Lin, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Rex Ying, Arman Cohan, Dragomir Radev
| Challenge: | Existing benchmarks for logical reasoning in large language models lack language naturalness or limited complexity. |
| Approach: | They propose to use first-order logic annotations to evaluate logical reasoning capabilities of large language models. |
| Outcome: | The proposed dataset evaluates the FOL reasoning ability of supervised fine-tuning on medium-sized language models. |
Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating rationales that justify scoring decisions are not accurate and often contain hallucinated information. |
| Approach: | They propose a framework capable of generating more faithful rationales and matching performance with classifier-based scoring systems. |
| Outcome: | The proposed framework achieves 38% improvement in QWK score compared to prior work . it can be used to match performance with classifier-based scoring systems . |
Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Current efforts in interpretability of medical coding rely heavily on label attention mechanisms, which often leads to the highlighting of extraneous tokens irrelevant to the ICD code. |
| Approach: | They propose to leverage dictionary learning to extract sparsely activated representations from dense language models embedded in superposition to facilitate accurate interpretability. |
| Outcome: | The proposed model extracts sparsely activated representations from dense language models in superposition, even when the highlighted tokens are medically irrelevant. |
TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification (2025.acl-long)
Copied to clipboard
Yindu Su, Huike Zou, Lin Sun, Ting Zhang, Haiyang Yang, Chen Li Yu, David Lo, Qingheng Zhang, Shuguang Han, Jufeng Chen
| Challenge: | Existing methods for product attribute value identification face critical challenges . seller-provided attribute values are often incomplete or inaccurate . |
| Approach: | They propose a retrieval-based method that uses taxonomy-aware contrastive learning . they use product profiles and candidate values to encode and retrieve attributes based on similarity . |
| Outcome: | The proposed method is based on a taxonomy-aware, hard negative sampling and adaptive inference with dynamic thresholds. |
Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe (2023.acl-long)
Copied to clipboard
Xiang Yue, Huseyin Inan, Xuechen Li, Girish Kumar, Julia McAnallen, Hoda Shajari, Huan Sun, David Levitan, Robert Sim
| Challenge: | Privacy concerns have increased in data-driven products due to the tendency of machine learning models to memorize sensitive training data. |
| Approach: | They propose a method for generating useful synthetic text with a formal privacy guarantee by fine-tuning a pretrained generative language model with DP. |
| Outcome: | The proposed method produces synthetic text competitive in terms of utility with its non-private counterpart, while providing strong protection against potential privacy leakages. |
Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMs (2025.naacl-short)
Copied to clipboard
| Challenge: | Large language models (LLMs) are widely used to simulate human responses, but their ability to account for demographic differences in subjective tasks remains uncertain. |
| Approach: | They evaluate large language models' ability to understand demographic differences in two subjective judgment tasks: politeness and offensiveness. |
| Outcome: | The proposed models perform better in politeness and offensiveness tasks, while sociodemographic prompting does not improve and worsens their ability to perceive language from sub-populations. |
MultiCodeAttack: Iterative Jailbreak Attacking on LLMs with Multi-Code Prompt Injection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to jailbreak rely on fixed template design and a single programming language . however, existing approaches do not consider language diversity or adaptive template evolution . |
| Approach: | They propose a structured jailbreak framework that explores and optimizes multi-language code templates. |
| Outcome: | The proposed framework outperforms existing jailbreak baselines and produces higher harmful outputs than baseline methods. |
Over-Searching in Search-Augmented Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Search-augmented large language models (LLMs) excel at knowledge-intensive tasks by integrating external retrieval. |
| Approach: | They conduct a systematic evaluation of over-searching across multiple dimensions including query types, model categories, retrieval conditions, and multi-turn conversations. |
| Outcome: | The proposed model improves answer accuracy on answerable queries but harms abstention on unanswerable ones . |
Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for evaluating item labels fail to leverage scenario-specific information modalities, present redundant information that is visually inferable, and lack latent awareness of users' information needs. |
| Approach: | They propose a principled categorization of information needs into explicit intent satisfaction and proactive information needs and define evaluation metrics for item label selection. |
| Outcome: | The proposed evaluation framework is based on IR-, LLM-, and VLM-based methods across fashion, movie recommendation, and retail shopping scenarios. |
TRACE: A Corpus of Team Creative Discussions (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on team creativity lack the ability to observe discussion dynamics from the perspective of natural language processing (NLP) Standard approaches capture participants' perceptions rather than actual behavior. |
| Approach: | They propose a corpus of 309 group discussions from 103 teams across six creative problem-solving tasks. |
| Outcome: | The proposed analysis reveals that large teams explore more broadly but converge less effectively while team diversity shapes participation patterns more than discussion content. |
Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)
Copied to clipboard
Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu
| Challenge: | Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent. |
| Approach: | They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs. |
| Outcome: | The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level models. |
DELPHI: Data for Evaluating LLMs’ Performance in Handling Controversial Issues (2023.emnlp-industry)
Copied to clipboard
| Challenge: | a recent study of controversy-handling in large language models (LLMs) has shown that people may become increasingly dependent on such systems for information. |
| Approach: | They propose to construct a controversial questions dataset using a subset of a publicly available dataset. |
| Outcome: | The proposed dataset presents challenges concerning knowledge recency, safety, fairness, and bias. |
DRGCoder: Explainable Clinical Coding for the Early Prediction of Diagnostic-Related Groups (2023.emnlp-demo)
Copied to clipboard
Daniel Hajialigol, Derek Kaknes, Tanner Barbour, Daphne Yao, Chris North, Jimeng Sun, David Liem, Xuan Wang
| Challenge: | Medical claim coding is the process of transforming medical records into structured codes in a classification system such as ICD-10 (International Classification of Diseases, Tenth Revision) or DRG (Diagnosis-Related Group) codes. |
| Approach: | They propose an explainability-enhanced clinical claim coding system for the early prediction of medical severity DRGs (MS-DRGs) a novel multi-task Transformer model allows users to inspect DRGCoder’s reasoning by visualizing the weights for each word of the input. |
| Outcome: | The proposed system allows users to analyze the weights of the input and compare across multiple discharge summaries. |
VoiceCraft-X: Unifying Multilingual, Voice-Cloning Speech Synthesis and Speech Editing (2025.emnlp-main)
Copied to clipboard
Zhisheng Zheng, Puyuan Peng, Anuj Diwan, Cong Phuoc Huynh, Xiaohang Sun, Zhu Liu, Vimal Bhat, David Harwath
| Challenge: | Autoregressive language model for multilingual speech editing and zero-shot text-to-speech synthesis is available in 11 languages. |
| Approach: | They introduce an autoregressive neural codec language model which unifies multilingual speech editing and zero-shot text-to-speech synthesis across 11 languages. |
| Outcome: | The model generates high-quality, natural-sounding speech, even with limited per-language data . it shows robust performance in diverse linguistic settings, even in limited per language data compared to other models . |