5 papers
AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Models
Zouying Cao, Yifei Yang, XiaoJing Li +1
Large language models (LLMs) have gained broad applications across various domains but still struggle with hallucinations. Currently, hallucinations occur frequently in the generat…
PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization
Zouying Cao, Runze Wang, Yifei Yang +4
Large Language Model (LLM) agents have demonstrated impressive capabilities in handling complex interactive problems. Existing LLM agents mainly generate natural language plans to…
How Deep is Love in LLMs' Hearts? Exploring Semantic Size in Human-like Cognition
Yao Yao, Yifei Yang, Xinbei Ma +4
How human cognitive abilities are formed has long captivated researchers. However, a significant challenge lies in developing meaningful methods to measure these complex processes.…
LESA: Learnable LLM Layer Scaling-Up
Yifei Yang, Zouying Cao, Xinbei Ma +4
Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leve…
SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering
Zouying Cao, Yifei Yang, Hai Zhao
Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to rej…