collaborators

6 papers

cs.CL2026

Can Released LLM Vocabularies Support Token-Level Estimation of Hidden Corpora?

Qingjie Zhang, Xingzhang Ren, Zixuan Chen +6

Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus mixtures or traced specific…

cs.LG2026

Knowing but Not Correcting: Routine Task Requests Suppress Factual Correction in LLMs

Zixuan Chen, Hao Lin, Zizhe Chen +6

LLMs reliably correct false claims when presented in isolation, yet when the same claims are embedded in task-oriented requests, they often comply rather than correct. We term this…

cs.MM2026

AVID: A Benchmark for Omni-Modal Audio-Visual Inconsistency Understanding via Agent-Driven Construction

Zixuan Chen, Depeng Wang, Hao Lin +6

We present AVID, the first large-scale benchmark for audio-visual inconsistency understanding in videos. While omni-modal large language models excel at temporally aligned tasks su…

cs.AI2026

Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure

Yida Lu, Jianwei Fang, Xuyang Shao +7

As Large Language Models (LLMs) evolve from chatbots to agentic assistants, they are increasingly observed to exhibit risky behaviors when subjected to survival pressure, such as t…

cs.CR2025

SDD: Self-Degraded Defense against Malicious Fine-tuning

Zixuan Chen, Weikai Lu, Xin Lin +1

Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLM…

cs.CL2025

Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraints

Zhengdong Lu, Weikai Lu, Yiling Tao +6

Despite significant advances in Large Language Models (LLMs), planning tasks still present challenges for LLM-based agents. Existing planning methods face two key limitations: heav…