5 papers
Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions
Yuntai Bao, Qinfeng Li, Xinyan Yu +6
Recently, steering vectors (SVs) have emerged as an effective and lightweight approach to steer behaviors of large language models (LLMs), among which fine-tuned SVs are more effec…
Speculating LLMs' Chinese Training Data Pollution from Their Tokens
Qingjie Zhang, Di Wang, Haoting Qian +7
Tokens are basic elements in the datasets for LLM training. It is well-known that many tokens representing Chinese phrases in the vocabulary of GPT (4o/4o-mini/o1/o3/4.5/4.1/o4-min…
Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models
Qingjie Zhang, Yujia Fu, Yang Wang +5
Current answering paradigms for Large Reasoning Models (LRMs) often fail to account for the fact that some questions may lie beyond the model's operational capability boundary, lea…
Enhancing Social Media Rumor Detection: A Semantic and Graph Neural Network Approach for the 2024 Global Election
Liu Yan, Liu Yunpeng, Zhao Liang
The development of social media platforms has revolutionized the speed and manner in which information is disseminated, leading to both beneficial and detrimental effects on societ…
A Probabilistic-Logic based Commonsense Representation Framework for Modelling Inferences with Multiple Antecedents and Varying Likelihoods
Shantanu Jaiswal, Liu Yan, Dongkyu Choi +1
Commonsense knowledge-graphs (CKGs) are important resources towards building machines that can 'reason' on text or environmental inputs and make inferences beyond perception. While…