Papers by Yiqun Sun

5 papers
STICKERCONV: Generating Multimodal Empathetic Responses from Scratch (2024.acl-long)

Copied to clipboard

Challenge: Prior studies on stickers focused on sentiment analysis and recommendation systems, overlooking their vast potential in empathetic response generation.
Approach: They propose a multimodal empathetic dialogue dataset, STICKERCONV, which simulates human behavior with stickers, and propose evaluative metrics based on LLM.
Outcome: The proposed framework generates contextually relevant and emotionally resonant multimodal empathetic responses, contributing to the advancement of more nuanced and engaging e-dialog systems.
Don’t Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space Transformation (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for text embedding require re-encoding the entire corpus for each instruction.
Approach: They propose a framework that generates dynamic text embeddings that adapt to user instructions, highlighting specific attributes of text.
Outcome: The proposed framework improves instruction-following text embedding quality over state-of-the-art methods while speeding up processing on large datasets.
If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for large language models (LLMs) fail to capture these dynamics, focusing on static, open-ended evaluations.
Approach: They propose a benchmark to assess lifelong learning in large language models . they use two episodic datasets rich in narrative structure and character interactions .
Outcome: Experiments on LLMs show that non-parametric methods outperform parametric ones in managing stateful learning.
PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder (2025.acl-long)

Copied to clipboard

Challenge: Existing embedding models excel at capturing general meaning, but overlook ideological nuances, limiting their effectiveness in political bias tasks.
Approach: They propose a framework to Produce inteRpretable polItical biaS eMbeddings.
Outcome: The proposed framework outperforms state-of-the-art embedding models in political bias classification . the proposed framework offers highly interpretable representations for political analysis .
Uncovering the Bigger Picture: Comprehensive Event Understanding Via Diverse News Retrieval (2025.emnlp-main)

Copied to clipboard

Challenge: Existing news retrieval systems prioritize textual relevance, leading to redundancy and limited viewpoint exposure.
Approach: They propose a framework that explicitly models semantic variation at the sentence level.
Outcome: The proposed framework outperforms strong baselines in terms of retrieval diversity without compromising relevance.

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