5 citations · 11 across the 13 of their papers we have counts for
14 papers
Lean Graph Search for Formal Theorem Proving
Yihan Xu, Jia-Chen Gu, Junyi Zhang +7
Retrieving relevant lemmas is crucial for formal theorem proving, enabling provers to build machine-checkable proofs from established mathematical results. Recent retrieval systems…
Planned Test-Time Scaling with Coordinated Reasoning Paths
Xueqing Wu, Langxing Bai, Hritik Bansal +5
Test-time scaling with parallel branches is widely adopted to improve performance on challenging reasoning tasks. The predominant approach, repeated sampling, draws branches indepe…
LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
Po-Nien Kung, Linfeng Song, Dawsen Hwang +10
Large Language Models (LLMs) exhibit strong informal mathematical reasoning but struggle to generate mechanically verifiable proofs in formal languages like Lean. We present LEAP,…
Learning Structured Reasoning via Tractable Trajectory Control
Po-Nien Kung, Zhen Yang, Jeffrey Luo +7
Large language models can exhibit emergent reasoning behaviors, often manifested as recurring lexical patterns (e.g., "wait," indicating verification). However, complex reasoning t…
LLM-REVal: Can We Trust LLM Reviewers Yet?
Rui Li, Jia-Chen Gu, Po-Nien Kung +5
The rapid advancement of large language models (LLMs) has inspired researchers to integrate them extensively into the academic workflow, potentially reshaping how research is pract…
Decoupling Task-Solving and Output Formatting in LLM Generation
Haikang Deng, Po-Nien Kung, Nanyun Peng
Large language models (LLMs) are increasingly adept at solving complex problems, such as mathematical reasoning and automatic evaluation. However, performance often degrades when p…
Adaptable Logical Control for Large Language Models
Honghua Zhang, Po-Nien Kung, Masahiro Yoshida +2
Despite the success of Large Language Models (LLMs) on various tasks following human instructions, controlling model generation at inference time poses a persistent challenge. In t…
GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling
Hritik Bansal, Po-Nien Kung, P. Jeffrey Brantingham +2
Multimodal event argument role labeling (EARL), a task that assigns a role for each event participant (object) in an image is a complex challenge. It requires reasoning over the en…
Improving Event Definition Following For Zero-Shot Event Detection
Zefan Cai, Po-Nien Kung, Ashima Suvarna +6
Existing approaches on zero-shot event detection usually train models on datasets annotated with known event types, and prompt them with unseen event definitions. These approaches…
Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks
Po-Nien Kung, Fan Yin, Di Wu +2
Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions. Howeve…
MIDDAG: Where Does Our News Go? Investigating Information Diffusion via Community-Level Information Pathways
Mingyu Derek Ma, Alexander K. Taylor, Nuan Wen +9
We present MIDDAG, an intuitive, interactive system that visualizes the information propagation paths on social media triggered by COVID-19-related news articles accompanied by com…
Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning
Po-Nien Kung, Nanyun Peng
Recent works on instruction tuning (IT) have achieved great performance with zero-shot generalizability to unseen tasks. With additional context (e.g., task definition, examples) p…
STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models
Mingyu Derek Ma, Xiaoxuan Wang, Po-Nien Kung +3
Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies. They heavily rely on task-specific traini…
Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems
Po-Nien Kung, Chung-Cheng Chang, Tse-Hsuan Yang +3
Task-oriented dialogue systems have been a promising area in the NLP field. Previous work showed the effectiveness of using a single GPT-2 based model to predict belief states and…