activity
20232025
most citedMINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback

16 citations · 39 across the 11 of their papers we have counts for

collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2025

Multimodal Policy Internalization for Conversational Agents

Zhenhailong Wang, Jiateng Liu, Amin Fazel +6

Modern conversational agents like ChatGPT and Alexa+ rely on predefined policies specifying metadata, response styles, and tool-usage rules. As these LLM-based systems expand to su…

cs.CL2025

ISACL: Internal State Analyzer for Copyrighted Training Data Leakage

Guangwei Zhang, Qisheng Su, Jiateng Liu +4

Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) but pose risks of inadvertently exposing copyrighted or proprietary data, especially when such da…

cs.CL2025

Atomic Reasoning for Scientific Table Claim Verification

Yuji Zhang, Qingyun Wang, Cheng Qian +7

Scientific texts often convey authority due to their technical language and complex data. However, this complexity can sometimes lead to the spread of misinformation. Non-experts a…

cs.CL2024

PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent

Jiateng Liu, Lin Ai, Zizhou Liu +6

Propaganda plays a critical role in shaping public opinion and fueling disinformation. While existing research primarily focuses on identifying propaganda techniques, it lacks the…

cs.CL2024★ 7 cited

Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models

Yuji Zhang, Sha Li, Jiateng Liu +5

Hallucination is often regarded as a major impediment for using large language models (LLMs), especially for knowledge-intensive tasks. Even when the training corpus consists solel…

cs.CL2024★ 1 cited

EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries

Jiateng Liu, Pengfei Yu, Yuji Zhang +3

The dynamic nature of real-world information necessitates efficient knowledge editing (KE) in large language models (LLMs) for knowledge updating. However, current KE approaches, w…