activity
20242026
most citedToo Good to be Bad: On the Failure of LLMs to Role-Play Villains

2 citations · 2 across the 5 of their papers we have counts for

collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL20252 cited

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

Zihao Yi, Qingxuan Jiang, Ruotian Ma +8

Large Language Models (LLMs) are increasingly tasked with creative generation, including the simulation of fictional characters. However, their ability to portray non-prosocial, an…

cs.CL2025

Attention Basin: Why Contextual Position Matters in Large Language Models

Zihao Yi, Delong Zeng, Zhenqing Ling +6

The performance of Large Language Models (LLMs) is significantly sensitive to the contextual position of information in the input. To investigate the mechanism behind this position…

cs.CL2024

Intent-driven In-context Learning for Few-shot Dialogue State Tracking

Zihao Yi, Zhe Xu, Ying Shen

Dialogue state tracking (DST) plays an essential role in task-oriented dialogue systems. However, user's input may contain implicit information, posing significant challenges for D…

cs.CL2024

Dynamic Demonstration Retrieval and Cognitive Understanding for Emotional Support Conversation

Zhe Xu, Daoyuan Chen, Jiayi Kuang +3

Emotional Support Conversation (ESC) systems are pivotal in providing empathetic interactions, aiding users through negative emotional states by understanding and addressing their…

cs.CL2024

A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems

Zihao Yi, Jiarui Ouyang, Zhe Xu +4

This survey provides a comprehensive review of research on multi-turn dialogue systems, with a particular focus on multi-turn dialogue systems based on large language models (LLMs)…