8 papers
Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing
Kexin Chen, Yi Liu, Haonan Zhang +3
As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern. Existing deception monitors either score visible transcripts or…
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Zelun Zhang, Hongen Liu, Suyin Liang +12
We introduce PaddleOCR-VL-1.6, an upgraded compact document parsing model built upon PaddleOCR-VL-1.5. Although PaddleOCR-VL-1.5 establishes a strong 0.9B baseline, its remaining e…
A Distribution-Free Framework for Rewrite-Based Human-text Detection via Knockoff Filtering
Yi Liu
We propose a distribution-free statistical framework that converts arbitrary rewrite-based detectors into detectors with finite-sample FDR guarantees without retraining. Our key ob…
UniRTL: Unifying Code and Graph for Robust RTL Representation Learning
Yi Liu, Hongji Zhang, Lei Chen +2
Developing effective representations for register transfer level (RTL) designs is crucial for accelerating the hardware design workflow. Existing approaches, however, typically rel…
LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment
Haonan Zhang, Dongxia Wang, Yi Liu +2
Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector steering methods adjust the mag…
ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal
Haonan Zhang, Dongxia Wang, Yi Liu +5
Large Language Models (LLMs) increasingly exhibit over-refusal - erroneously rejecting benign queries due to overly conservative safety measures - a critical functional flaw that u…
Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models
Kexin Chen, Dongxia Wang, Yi Liu +2
Despite the widespread use of Transformer-based text embedding models in NLP tasks, surprising 'sticky tokens' can undermine the reliability of embeddings. These tokens, when repea…
Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks
Kexin Chen, Yi Liu, Dongxia Wang +2
Large Language Models (LLMs) have increasingly become pivotal in content generation with notable societal impact. These models hold the potential to generate content that could be…