6 papers · 1 filter
BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods
Philipp Mondorf, Mingyang Wang, Sebastian Gerstner +6
The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB) evaluates methods for localizing circuits within large language models (LLMs), i.e., subnetworks…
Refusal Direction is Universal Across Safety-Aligned Languages
Xinpeng Wang, Mingyang Wang, Yihong Liu +2
Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in ac…
Tracing Multilingual Factual Knowledge Acquisition in Pretraining
Yihong Liu, Mingyang Wang, Amir Hossein Kargaran +5
Large Language Models (LLMs) are capable of recalling multilingual factual knowledge present in their pretraining data. However, most studies evaluate only the final model, leaving…
Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior
Shengyun Si, Xinpeng Wang, Guangyao Zhai +2
Recent advancements in large language models (LLMs) have demonstrated that fine-tuning and human alignment can render LLMs harmless. In practice, such "harmlessness" behavior is ma…
M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis
Chengyan Wu, Bolei Ma, Yihong Liu +7
Aspect-based sentiment analysis (ABSA) is a crucial task in information extraction and sentiment analysis, aiming to identify aspects with associated sentiment elements in text. Ho…
Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
Xinpeng Wang, Chengzhi Hu, Paul Röttger +1
Training a language model to be both helpful and harmless requires careful calibration of refusal behaviours: Models should refuse to follow malicious instructions or give harmful…