Papers by Xingyao Wang

11 papers
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

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

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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations