Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance
Bar Alon, Itamar Zimerman, Lior Wolf
Large language models (LLMs) achieve strong performance and have revolutionized NLP, but their lack of explainability keeps them treated as black boxes, limiting their use in domai…
cs.CL2024
Mitigating Copy Bias in In-Context Learning through Neuron Pruning
Ameen Ali, Lior Wolf, Ivan Titov
Large language models (LLMs) have demonstrated impressive few-shot in-context learning (ICL) abilities. Still, we show that they are sometimes prone to a `copying bias', where they…