Pietro Bernardelle
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Info Retrieval×1
Frequent co-authors
Research Timeline
2026
LLMs Encode Relevance as a Layer-Wise Cross-Lingual Signal
This paper studies the linear decodability of query-document relevance from residual-stream activations in instruction-tuned large language models (LLMs) and compares it with generated relevance judgments.
Highlighted terms show continued research focus across papers