SOTAVerified

TriviaQA

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 124 papers

TitleStatusHype
Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds—0
GenKI: Enhancing Open-Domain Question Answering with Knowledge Integration and Controllable Generation in Large Language ModelsCode0
HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation—0
Semantic Caching of Contextual Summaries for Efficient Question-Answering with Language Models—0
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures—0
ShED-HD: A Shannon Entropy Distribution Framework for Lightweight Hallucination Detection on Edge Devices—0
CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation—0
Cost-Saving LLM Cascades with Early Abstention—0
Self-Training Large Language Models for Tool-Use Without Demonstrations—0
Vision-centric Token Compression in Large Language Model—0
ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrieval—0
Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation—0
DragonVerseQA: Open-Domain Long-Form Context-Aware Question-AnsweringCode0
Layer Importance and Hallucination Analysis in Large Language Models via Enhanced Activation Variance-Sparsity—0
Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI—0
Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation—0
KV Prediction for Improved Time to First TokenCode0
Exploring Hint Generation Approaches in Open-Domain Question AnsweringCode1
SFR-RAG: Towards Contextually Faithful LLMs—0
FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence SelectionCode1
Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting—0
From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic DataCode0
Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-JudgesCode0
CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAGCode0
RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented GenerationCode0
Show:102550
← PrevPage 1 of 5Next →

No leaderboard results yet.