6 papers
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…
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…
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…
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…
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…
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…