7 papers
Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
Sicheng Wang, Xiangyang Zhu, Han Wang +6
Prior work has shown that fine-tuning large language models on malicious or incorrect outputs in narrow domains can induce broad misalignment and harmful behavior, a phenomenon kno…
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
Xiangyang Zhu, Yuan Tian, Qi Jia +14
The success of large language models (LLMs) in scientific domains has heightened safety concerns, prompting numerous benchmarks to evaluate their scientific safety. Existing benchm…
A: Towards Advertising Aesthetic Assessment
Kaiyuan Ji, Yixuan Gao, Lu Sun +7
Advertising images significantly impact commercial conversion rates and brand equity, yet current evaluation methods rely on subjective judgments, lacking scalability, standardized…
PriceSeer: Evaluating Large Language Models in Real-Time Stock Prediction
Bohan Liang, Zijian Chen, Qi Jia +3
Stock prediction, a subject closely related to people's investment activities in fully dynamic and live environments, has been widely studied. Current large language models (LLMs)…
MedOmni-45°: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine
Kaiyuan Ji, Yijin Guo, Zicheng Zhang +4
With the increasing use of large language models (LLMs) in medical decision-support, it is essential to evaluate not only their final answers but also the reliability of their reas…
Research-Oriented Human-Centric Evaluation for Foundation Models
Yijin Guo, Kaiyuan Ji, Xiaorong Zhu +5
Most current evaluations of foundation models focus on objective benchmarks, such as knowledge coverage and reasoning accuracy, often overlooking users' subjective experiences in h…