Papers by Haiming Qin

6 papers
Prototype-based Prompt-Instance Interaction with Causal Intervention for Few-shot Event Detection (2024.lrec-main)

Copied to clipboard

Challenge: Few-shot Event Detection (FSED) requires limited labeled data and expensive manual labeling.
Approach: They propose a prototype-based prompt-instance Interaction with causal Intervention model to utilize both prompts and verbalizers and effectively eliminate all biases.
Outcome: The proposed model utilizes both prompts and verbalizers and eliminates all biases on RAMS and ACE datasets.
Knowing-but-Doing: Diagnosing and Defending Role-Play-Driven LLMs Jailbreaks via Moral Disengagement (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly used in role-play scenarios, but their safety implications remain under-characterized.
Approach: They propose a diagnostic benchmark for role-play jailbreaks based on Bandura’s Moral Disengagement theory and propose 'MD-Trace' based defense that reduces attack success while maintaining Role Fidelity.
Outcome: The proposed framework improves safety behavior for benign personas while increasing unsafe compliance for malicious ones.
Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to learn internal world models rely on one-step supervision . however, standard MTP suffers from structural hallucinations .
Approach: They propose a method which anchors predictions to ground-truth hidden state trajectories.
Outcome: The proposed method bridges the gap between discrete tokens and continuous state representations, reducing structural hallucinations, and improving robustness to perturbations.
PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing research focuses on character-level settings and static evaluation formats fail to capture the complexity of everyday social interactions.
Approach: They propose a dynamic simulation framework for evaluating and improving persona-level role-playing in large language models (LLMs).
Outcome: The proposed framework leverages user-generated social content to construct a nuanced persona bank and elicits multi-turn, context-rich interactions within simulated social environments.
Hierarchical Reward Modeling for Fault Localization in Large Code Repositories (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have limited fault localization capabilities due to limited context length.
Approach: They propose a hierarchical localization reward model to evaluate and select the most accurate fault localization candidates from the outputs of LLMs.
Outcome: The proposed model improves the final line-level localization recall by 12% on the SWE-Bench-Lite dataset.
R-CHAR: A Metacognition-Driven Framework for Role-Playing in Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing role-playing structures lack cognitive consistency in complex scenarios . Existing models excel in math and coding tasks but lack coherent reasoning .
Approach: They propose a metacognition-driven framework that enhances role-playing performance . experimental results show performance improvements across varying scenario complexities .
Outcome: The proposed framework outperforms existing models in social intelligence tasks and shows strength in long-context comprehension and group-level social interactions.

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