7 papers
ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu +8
LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate…
Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet
James Xu Zhao, Bryan Hooi, See-Kiong Ng
Test-time scaling increases inference-time computation through longer reasoning chains and has shown strong performance gains across many domains. However, frontier models still su…
How Does Response Length Affect Long-Form Factuality
James Xu Zhao, Jimmy Z. J. Liu, Bryan Hooi +1
Large language models (LLMs) are widely used for long-form text generation. However, factual errors in the responses would undermine their reliability. Despite growing attention to…
Geneshift: Impact of different scenario shift on Jailbreaking LLM
Tianyi Wu, Zhiwei Xue, Yue Liu +3
Jailbreak attacks, which aim to cause LLMs to perform unrestricted behaviors, have become a critical and challenging direction in AI safety. Despite achieving the promising attack…
Spatio-Temporal Foundation Models: Vision, Challenges, and Opportunities
Adam Goodge, Wee Siong Ng, Bryan Hooi +1
Foundation models have revolutionized artificial intelligence, setting new benchmarks in performance and enabling transformative capabilities across a wide range of vision and lang…
Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning
Tianyi Wu, Jingwei Ni, Bryan Hooi +5
Instruction fine-tuning (IFT) can increase the informativeness of large language models (LLMs), but may reduce their truthfulness. This trade-off arises because IFT steers LLMs to…
Global Challenge for Safe and Secure LLMs Track 1
Xiaojun Jia, Yihao Huang, Yang Liu +27
This paper introduces the Global Challenge for Safe and Secure Large Language Models (LLMs), a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme…