Chain-of-illocution prompting improves source adherence in RAG explanations for programming education by up to 63% over baselines.
Title resolution pending
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
BrowseComp-ZH is a new benchmark of 289 Chinese web questions where even the strongest LLM agents reach only 42.9% accuracy.
VisRAG achieves 20-40% better end-to-end performance than text-based RAG by directly embedding and retrieving document images with VLMs.
Hallucinations are inevitable in LLMs because they cannot learn all computable functions according to learning theory.
A principled reward design for tool selection and application in RL-trained LLMs delivers 17% gains over base models and 15% over SFT across benchmarks.
SimpleQA is a new benchmark of short, single-answer factual questions collected adversarially against GPT-4 to evaluate LLM factuality and confidence calibration.
The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt utility.
QuestBench is a student-constructed benchmark of 256 questions on which current deep research AI systems achieve a mean pass rate of 16.85% and a best-case rate of 57.58%.
citing papers explorer
-
Retrieval-Augmented Generation for Natural Language Processing: A Survey
The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.
-
TrustLLM: Trustworthiness in Large Language Models
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt utility.