Papers by Xingyao Wang
Making Pre-trained Language Models both Task-solvers and Self-calibrators (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work shows that pre-trained language models can be effective for high-stake applications, but they become overconfident in their wrong predictions. |
| Approach: | They propose to use extra data to train pre-trained language models to effectively utilize training samples to make them both task-solvers and self-calibrators. |
| Outcome: | The proposed method can be used in three downstream applications, including selective classification, adversarial defense, and model cascading. |
Coding Agents with Multimodal Browsing are Generalist Problem Solvers (2026.findings-eacl)
Copied to clipboard
| Challenge: | specialized AI agents with task-specific tools or architectures fail to generalize beyond their intended scope. |
| Approach: | They propose a single-agent system with a modest number of general tools . they propose to generalize across software engineering, deep research and web browsing . |
| Outcome: | The proposed system achieves superior or competitive performance over specialized agents on three benchmarks. |
Code4Struct: Code Generation for Few-Shot Event Structure Prediction (2023.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) trained on a mixture of text and code have demonstrated impressive capability in translating natural language (NL) into structured code. |
| Approach: | They propose to use programming language (PL) inheritance and type annotations to translate text into code to tackle structured prediction tasks. |
| Outcome: | The proposed model outperforms existing models on 20-shot data by 29.5% absolute F1. |
R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’ (2024.naacl-long)
Copied to clipboard
Hanning Zhang, Shizhe Diao, Yong Lin, Yi Fung, Qing Lian, Xingyao Wang, Yangyi Chen, Heng Ji, Tong Zhang
| Challenge: | Existing methods for instruction tuning force the model to complete a sentence no matter whether it knows the knowledge or not. |
| Approach: | They propose a new approach to tuning large language models to refrain from answering questions beyond its parametric knowledge by identifying the disparity in parametric and parametric information. |
| Outcome: | The proposed approach improves a model’s ability to answer known questions and refrain from answering unknown questions. |
SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to elicit confidence from large language models are limited to binary or inaccurate group-level confidence estimates. |
| Approach: | They propose a training framework that teaches LLMs to express more fine-grained confidence estimates. |
| Outcome: | The proposed training framework reduces the confidence calibration error and maintains the performance of the model. |
An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Increasingly, image-based responses such as memes and animated gifs serve as culturally recognized and often humorous responses in conversation. |
| Approach: | They propose a multimodal conversational model for selecting gif responses from a text-gif conversation turn dataset and a randomized controlled trial. |
| Outcome: | The proposed model produces relevant and high-quality gif responses and is significantly better received by the community. |
Defining a New NLP Playground (2023.findings-emnlp)
Copied to clipboard
Sha Li, Chi Han, Pengfei Yu, Carl Edwards, Manling Li, Xingyao Wang, Yi Fung, Charles Yu, Joel Tetreault, Eduard Hovy, Heng Ji
| Challenge: | Recent explosion of performance of large language models (LLMs) has changed the field more abruptly and seismically than any other shift in the field’s 80 year history. |
| Approach: | They propose 20+ PhD-dissertation-worthy research directions to define a new NLP playground by combining theoretical analysis, new and challenging problems, learning paradigms and interdisciplinary applications. |
| Outcome: | The proposed research will cover theoretical analysis, new and challenging problems, learning paradigms and interdisciplinary applications. |
LocAgent: Graph-Guided LLM Agents for Code Localization (2025.acl-long)
Copied to clipboard
Zhaoling Chen, Robert Tang, Gangda Deng, Fang Wu, Jialong Wu, Zhiwei Jiang, Viktor Prasanna, Arman Cohan, Xingyao Wang
| Challenge: | Existing approaches struggle to efficiently navigate complex codebases when identifying relevant code snippets. |
| Approach: | They propose a graph-guided agent framework that addresses code localization through a distributed graph-based agent. |
| Outcome: | The proposed framework improves accuracy on real-world benchmarks and can be used to locate code snippets at a cost of 86%. |
LETI: Learning to Generate from Textual Interactions (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing techniques fine-tune on input-output pairs or with numerical rewards that gauge the output quality are not effective. |
| Approach: | They propose to fine-tune pre-trained language models with binary labels and a Python interpreter to get textual feedback from the inputs. |
| Outcome: | The proposed model outperforms the base model on unseen problems and achieves comparable or better performance on humanEval. |
POTATO: The Portable Text Annotation Tool (2022.emnlp-demos)
Copied to clipboard
Jiaxin Pei, Aparna Ananthasubramaniam, Xingyao Wang, Naitian Zhou, Apostolos Dedeloudis, Jackson Sargent, David Jurgens
| Challenge: | POTATO is a free, fully open-sourced annotation system that supports labeling many types of text and multimodal data. |
| Approach: | They propose to use POTATO to design and deploy complex annotation tasks. |
| Outcome: | The proposed annotation system improves labeling speed and productivity over two tasks. |
ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation (2023.emnlp-main)
Copied to clipboard
| Challenge: | State-of-the-art vision-language models have limited performance in structural knowledge extraction, such as relations between objects. |
| Approach: | They propose to leverage the inherent structure of programming language to depict visual structural information in a well-organized structured format. |
| Outcome: | The proposed framework improves visual structural knowledge extraction on visual structure prediction tasks. |