19 citations · 28 across the 15 of their papers we have counts for
6 papers · 1 filter
How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs
Shivam Adarsh, Maria Maistro, Christina Lioma
Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations. These vectors, also known as truth vectors, have been studie…
As easy as PIE: understanding when pruning causes language models to disagree
Pietro Tropeano, Maria Maistro, Tuukka Ruotsalo +1
Language Model (LM) pruning compresses the model by removing weights, nodes, or other parts of its architecture. Typically, pruning focuses on the resulting efficiency gains at the…
A Reality Check on Context Utilisation for Retrieval-Augmented Generation
Lovisa Hagström, Sara Vera Marjanović, Haeun Yu +5
Retrieval-augmented generation (RAG) helps address the limitations of parametric knowledge embedded within a language model (LM). In real world settings, retrieved information can…
DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models
Sara Vera Marjanović, Haeun Yu, Pepa Atanasova +3
Knowledge-intensive language understanding tasks require Language Models (LMs) to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated k…
Query Augmentation by Decoding Semantics from Brain Signals
Ziyi Ye, Jingtao Zhan, Qingyao Ai +4
Query augmentation is a crucial technique for refining semantically imprecise queries. Traditionally, query augmentation relies on extracting information from initially retrieved,…
BrainLLM: Generative Language Decoding from Brain Recordings
Ziyi Ye, Qingyao Ai, Yiqun Liu +4
Generating human language through non-invasive brain-computer interfaces (BCIs) has the potential to unlock many applications, such as serving disabled patients and improving commu…