Papers by Yunhe Pang

5 papers
RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for understanding research papers offer limited fine-grained evaluation at scale.
Approach: They propose a large-scale question-answering benchmark built from review–rebuttal exchanges of high-quality computer science papers.
Outcome: The proposed model is based on human-verified QA pairs and contains 15K questions.
CoE: A Clue of Emotion Framework for Emotion Recognition in Conversations (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are limited in interpreting complex conversational streams.
Approach: They propose a Clue of Emotion framework which integrates key conversational clues to enhance the ERC task.
Outcome: The proposed framework outperforms EmoryNLP, MELD, and IEMOCAP in the role-playing, speaker identification, and emotion reasoning tasks.
HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions (2026.acl-long)

Copied to clipboard

Challenge: Multi-Hop Question Answering (MHQA) is a critical benchmark for evaluating the model’s ability to integrate information from diverse sources.
Approach: They propose a framework that synthesizes authentic multi-hop questions without manual annotation without the need for manual guidance.
Outcome: The proposed framework synthesizes bridge and comparison questions without human intervention and achieves comparable or superior quality to human-annotated datasets at a lower cost.
CARE: A Disagreement Detection Framework with Concept Alignment and Reasoning Enhancement (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to disagreement detection are limited by conceptual gap and reasoning gap.
Approach: They propose a conceptual alignment and reasoning enhancement framework to address the conceptual gap and the reasoning gap in disagreement detection.
Outcome: The proposed framework shows superior performance in zero-shot and supervised learning settings, both within and across domains.
Learnable Dependency-based Double Graph Structure for Aspect-based Sentiment Analysis (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for aspect-based sentiment classification are susceptible to dependency tree due to noisy information and neglecting rich relation information between words.
Approach: They propose a dependency-based double graph model for aspect-based sentiment classification that incorporates structure, relations and linguistic features into the sentiment text.
Outcome: The proposed model is superior to state-of-the-art methods on four benchmark datasets.

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