Papers by Zhiyu Shen

6 papers
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.
PATIENT-๐œ“: Using Large Language Models to Simulate Patients for Training Mental Health Professionals (2024.emnlp-main)

Copied to clipboard

Challenge: Mental illness remains one of the most critical public health issues.
Approach: They propose a patient simulation framework for cognitive behavior therapy training that uses large language models to act as a simulated therapy patient.
Outcome: The proposed framework improves the skill acquisition and confidence of mental health trainees beyond textbooks, videos, and role-play with non-patients.
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 modelโ€™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.
How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection (N19-1)

Copied to clipboard

Challenge: Using a pre-defined vocabulary is a common approach to selecting text inputs . however, using a large vocabulary is not economical, as it limits the model's applicability on computation-or memoryconstrained scenarios.
Approach: They propose a more sophisticated variational vocabulary dropout to perform vocabulary selection . they propose two new metrics to measure area under accuracy-vocab curve and Vocab Size under X% accuracy drop .
Outcome: The proposed framework outperforms the baselines on the vocabulary selection problem on multiple NLP classification tasks.
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.
MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards (2026.acl-long)

Copied to clipboard

Challenge: Memory-augmented frameworks fail to capture temporal evolution of historical states, limiting consistency in long-term dialogues.
Approach: They propose a framework that trains models to orchestrate multi-dimensional memory construction with attributed dense rewards.
Outcome: The proposed framework outperforms state-of-the-art closed-source models and generalizes well to OOD benchmarks.

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