Papers with Code 아카이브

TriviaQA

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

1

보존된 평가 기록

1

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds

GenKI: Enhancing Open-Domain Question Answering with Knowledge Integration and Controllable Generation in Large Language Models

HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation

Semantic Caching of Contextual Summaries for Efficient Question-Answering with Language Models

DYNAMAX: Dynamic computing for Transformers and Mamba based architectures

ShED-HD: A Shannon Entropy Distribution Framework for Lightweight Hallucination Detection on Edge Devices

CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation

Cost-Saving LLM Cascades with Early Abstention

Self-Training Large Language Models for Tool-Use Without Demonstrations

Vision-centric Token Compression in Large Language Model

ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrieval

Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation

DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering

Layer Importance and Hallucination Analysis in Large Language Models via Enhanced Activation Variance-Sparsity

Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI

Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation

KV Prediction for Improved Time to First Token

Exploring Hint Generation Approaches in Open-Domain Question Answering

SFR-RAG: Towards Contextually Faithful LLMs

FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data

Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges

CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG

RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation

Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs

LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models

Accurate and Nuanced Open-QA Evaluation Through Textual Entailment

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

KS-LLM: Knowledge Selection of Large Language Models with Evidence Document for Question Answering

Mitigating LLM Hallucinations via Conformal Abstention

Multi-Granularity Guided Fusion-in-Decoder

FIT-RAG: Black-Box RAG with Factual Information and Token Reduction

Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering

Unfamiliar Finetuning Examples Control How Language Models Hallucinate

Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.