RAG with top-3 chunk retrieval lifts smaller LLMs on Indian legal QA (Llama2-70B: 45.7% to 51.7% on AIBE) but often hurts large models, and under the study's own rating protocol some AI answers outscored the reference lawyer answers.
KPQA : A Metric for Generative Question Answering Using Keyphrase Weights
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System
RAG with top-3 chunk retrieval lifts smaller LLMs on Indian legal QA (Llama2-70B: 45.7% to 51.7% on AIBE) but often hurts large models, and under the study's own rating protocol some AI answers outscored the reference lawyer answers.