7 papers
SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics
Haolong Hu, Hanyu Li, Tiancheng He +6
MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploit long-context safety decay. Y…
Revisiting a Pain in the Neck: A Semantic Reasoning Benchmark for Language Models
Yang Liu, Hongming Li, Melissa Xiaohui Qin +2
We present SemanticQA, an evaluation suite designed to assess language models (LMs) in semantic phrase processing tasks. The benchmark consolidates existing multiword expression (M…
LACE: Lattice Attention for Cross-thread Exploration
Yang Li, Zirui Zhang, Yang Liu +1
Current large language models reason in isolation. Although it is common to sample multiple reasoning paths in parallel, these trajectories do not interact, and often fail in the s…
M100: An Orchestrated Dataflow Architecture Powering General AI Computing
Yan Xie, Changkui Mao, Changsong Wu +34
As deep learning-based AI technologies gain momentum, the demand for general-purpose AI computing architectures continues to grow. While GPGPU-based architectures offer versatility…
Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
Jingyi Ren, Ante Wang, Yunghwei Lai +5
Reliable Large Language Models (LLMs) should abstain when confidence is insufficient. However, prior studies often treat refusal as a generic "I don't know'', failing to distinguis…
Structural Anchors and Reasoning Fragility:Understanding CoT Robustness in LLM4Code
Yang Liu, Da Song, Armstrong Foundjem +2
Chain-of-Thought (CoT) prompting is widely used to elicit explicit reasoning from large language models for code (LLM4Code). However, its impact on robustness and the stability of…