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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/Aatrox103/CrAM

공식 코드

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

https://github.com/DeepLearnXMU/QGC

공식 코드

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

https://github.com/HongyuGong/RCM-Question-Answering

공식 코드

Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension

https://github.com/KNOT-FIT-BUT/R2-D2

공식 코드

R2-D2: A Modular Baseline for Open-Domain Question Answering

https://github.com/NVIDIA/Megatron-LM

공식 코드

End-to-End Training of Neural Retrievers for Open-Domain Question Answering

https://github.com/U-Alberta/QA-partial-marks

공식 코드

Accurate and Nuanced Open-QA Evaluation Through Textual Entailment

https://github.com/UMass-Meta-LLM-Eval/llm_eval

공식 코드

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

https://github.com/abdoelsayed2016/grg

공식 코드

Generator-Retriever-Generator Approach for Open-Domain Question Answering

https://github.com/alibaba/AliceMind/tree/main/StructBERT

공식 코드

Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering

https://github.com/allenai/document-qa

공식 코드

Simple and Effective Multi-Paragraph Reading Comprehension

https://github.com/allenai/longformer

공식 코드

Longformer: The Long-Document Transformer

https://github.com/amzn/refuel-open-domain-qa

공식 코드

Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction

https://github.com/apple/corenet

공식 코드

KV Prediction for Improved Time to First Token

https://github.com/aritra23/dragonverseqa

공식 코드

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

https://github.com/datascienceuibk/hintqa

공식 코드

Exploring Hint Generation Approaches in Open-Domain Question Answering

https://github.com/edixiong/artificial-needles

공식 코드

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

https://github.com/edward-sun/recite

공식 코드

Recitation-Augmented Language Models

https://github.com/esteng/pragmatic_calibration

공식 코드

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

https://github.com/ethanleo-lyx/llmqa

공식 코드

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

https://github.com/eunseongc/mgfid

공식 코드

Multi-Granularity Guided Fusion-in-Decoder

https://github.com/facebookresearch/layerskip

공식 코드

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

https://github.com/h19920918/emr

공식 코드

Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data

https://github.com/hao-cheng/ds_doc_qa

공식 코드

Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering

https://github.com/huminghao16/RE3QA

공식 코드

Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

https://github.com/jd-ai-research-nlp/ror

공식 코드

RoR: Read-over-Read for Long Document Machine Reading Comprehension

https://github.com/jerrrynie/diverseqa

공식 코드

Unsupervised Question Answering via Answer Diversifying

https://github.com/katiekang1998/llm_hallucinations

공식 코드

Unfamiliar Finetuning Examples Control How Language Models Hallucinate

https://github.com/kkskp/re-rag

공식 코드

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

https://github.com/likicode/QA-generalize

공식 코드

Challenges in Generalization in Open Domain Question Answering

https://github.com/michiyasunaga/LinkBERT

공식 코드

LinkBERT: Pretraining Language Models with Document Links

https://github.com/microsoft/ProphetNet

공식 코드

CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

https://github.com/microsoft/ar2

공식 코드

Adversarial Retriever-Ranker for dense text retrieval

https://github.com/microsoft/simxns

공식 코드

Allies: Prompting Large Language Model with Beam Search

https://github.com/mlo-lab/bvcd_generative_models

공식 코드

A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models

https://github.com/morningmoni/GAR

공식 코드

Generation-Augmented Retrieval for Open-domain Question Answering

https://github.com/nkandpa2/long_tail_knowledge

공식 코드

Large Language Models Struggle to Learn Long-Tail Knowledge

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