most citedAggTruth: Contextual Hallucination Detection using Aggregated Attention Scores in LLMs

1 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2025★ 1 cited

Divide, Cache, Conquer: Dichotomic Prompting for Efficient Multi-Label LLM-Based Classification

Mikołaj Langner, Jan Eliasz, Ewa Rudnicka +1

We introduce a method for efficient multi-label text classification with large language models (LLMs), built on reformulating classification tasks as sequences of dichotomic (yes/n…