Papers by Mengxiao Song

2 papers
SOTOPIA-: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents (2025.acl-long)

Copied to clipboard

Challenge: Existing studies on the social simulation of large language model intelligent agents have shown that even expert agents 1 perform significantly worse on challenging social tasks compared to expert agents.
Approach: They propose a framework that dynamically injects a variety of social strategies into expert agents, thereby automating the construction of high-quality social dialogue training corpus.
Outcome: The proposed framework enables the integration of social strategies into language agents and improves their performance on social tasks.
Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot Co-occurrence (2022.emnlp-main)

Copied to clipboard

Challenge: Existing joint models only use training procedure to determine the implicit correlation between intents and slots.
Approach: They propose to make full use of the statistical co-occurrence frequency between intents and slots as prior knowledge to enhance joint multiple intent detection and slot filling.
Outcome: The proposed model outperforms state-of-the-art models on two public multi-intent 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