Papers by Tiantian Zhang

5 papers
Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing offline approaches to improve an LLM-based customer support system rely on batch annotations.
Approach: They propose an agent-in-the-loop framework that integrates four key types of annotations directly into live customer operations: (1) pairwise response preferences, (2) agent adoption and rationales, (3) knowledge relevance checks, and (4) identification of missing knowledge.
Outcome: The proposed framework reduces retraining cycles from months to weeks by integrating four key types of annotations directly into live customer operations.
RespiraMFM: A Multimodal Foundation Model with Contrastive Audio-Language Alignment for Respiratory Disease Identification (2026.acl-long)

Copied to clipboard

Challenge: Existing models for respiratory diseases rely on audio inputs, but they lack generalizability and diagnostic precision.
Approach: They propose a multimodal foundation model that integrates respiratory sounds with medical history and symptoms to enhance diagnostic accuracy and disease detection capabilities.
Outcome: The proposed model improves AUROC and zero-shot tasks across five respiratory diseases using real-world datasets.
Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding (2025.findings-acl)

Copied to clipboard

Challenge: a new study examines the performance of large vision-language models in understanding art . the Pun Rebus Art Dataset is a multimodal dataset for art understanding rooted in traditional Chinese culture .
Approach: They propose a multimodal dataset for art understanding deeply rooted in traditional Chinese culture . they aim to facilitate the development of VLMs that can better understand culturally specific content .
Outcome: The proposed dataset shows that state-of-the-art VLMs struggle with these tasks . the data will facilitate the development of VLM models that can better understand culturally specific content .
Why Do Emotions Change? Appraisal-Guided Reasoning for Emotion–Cause Triplet Extraction in Conversations (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for multi-turn, multi-speaker multimodal affect understanding are difficult to maintain conversation-level consistency under within-speaks' emotion shifts.
Approach: They propose a framework that combines appraisal-guided structured generation with graph-structured reinforcement learning to extract triplets from multi-turn multimodal conversations.
Outcome: The proposed framework outperforms baselines on public MECTEC benchmarks and improves structure-aware metrics on emotion shift coherence and core events.
M3HG: Multimodal, Multi-scale, and Multi-type Node Heterogeneous Graph for Emotion Cause Triplet Extraction in Conversations (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for ECAC focus on textual contexts, overlooking other modalities.
Approach: They propose a multimodal, multi-scenario MECTEC dataset that captures emotional and causal contexts and effectively fuses contextual information at different levels.
Outcome: The proposed model captures emotional and causal contexts and effectively fuses contextual information at both inter- and intra-utterance levels.

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