8 papers
Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?
Ziqian Zhong, Aashiq Muhamed, Mona T. Diab +2
Mechanistic interpretability is often motivated for alignment auditing, where a model's verbal explanations can be absent, incomplete, or misleading. Yet many evaluations do not co…
RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
Aashiq Muhamed, Leonardo F. R. Ribeiro, Markus Dreyer +2
The ability of language models in RAG systems to selectively refuse to answer based on flawed context is critical for safety, yet remains a significant failure point. Our large-sca…
Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Language
Mena Attia, Aashiq Muhamed, Mai Alkhamissi +2
We present a comprehensive evaluation of the ability of large language models (LLMs) to process culturally grounded language, specifically to understand and pragmatically use figur…
CCRS: A Zero-Shot LLM-as-a-Judge Framework for Comprehensive RAG Evaluation
Aashiq Muhamed
RAG systems enhance LLMs by incorporating external knowledge, which is crucial for domains that demand factual accuracy and up-to-date information. However, evaluating the multifac…
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
Xiangchen Song, Aashiq Muhamed, Yujia Zheng +5
Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration…
CoRAG: Collaborative Retrieval-Augmented Generation
Aashiq Muhamed, Mona Diab, Virginia Smith
Retrieval-Augmented Generation (RAG) models excel in knowledge-intensive tasks, especially under few-shot learning constraints. We introduce CoRAG, a framework extending RAG to col…