RISC reformulates self-consistency answer selection as a ranking task solved by a lightweight LambdaRank model with five hand-designed features, yielding better accuracy-efficiency trade-offs than majority voting on QA benchmarks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SEEK uses adaptive semantic chunking to create complete evidence units and fine-tunes multilingual LLMs with LoRA, achieving up to 20% better macro-F1 on fact-checking datasets compared to baselines.
citing papers explorer
-
Boosting Self-Consistency with Ranking
RISC reformulates self-consistency answer selection as a ranking task solved by a lightweight LambdaRank model with five hand-designed features, yielding better accuracy-efficiency trade-offs than majority voting on QA benchmarks.
-
SEEK: Semantic Evidence Extraction via Adaptive ChunKing for Multilingual Fact-Checking
SEEK uses adaptive semantic chunking to create complete evidence units and fine-tunes multilingual LLMs with LoRA, achieving up to 20% better macro-F1 on fact-checking datasets compared to baselines.