Papers with Code 아카이브

Question Answering

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 19
평가표: 153
보존된 평가 기록: 1,781

Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include SQuAD, HotPotQA, bAbI, TriviaQA, WikiQA, and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.

( Image credit: SQuAD )

코드

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

https://github.com/ruochenzhao/verify-and-edit

공식 코드

Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework

https://github.com/ruoxi-jia-group/2dshapley

공식 코드

2D-Shapley: A Framework for Fragmented Data Valuation

https://github.com/rupertluo/valley

공식 코드

Valley: Video Assistant with Large Language model Enhanced abilitY

https://github.com/russellyq/medhalltune

공식 코드

MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models

https://github.com/ryanwangzf/biobridge

공식 코드

BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs

https://github.com/ryokamoi/qa-metrics-human-annotation

공식 코드

Shortcomings of Question Answering Based Factuality Frameworks for Error Localization

https://github.com/ryokamoi/wice

공식 코드

WiCE: Real-World Entailment for Claims in Wikipedia

https://github.com/s-nlp/konstruktor

공식 코드

Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering

https://github.com/s1s-z/canoe

공식 코드

Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning

https://github.com/s3vqa/s3vqa.github.io

공식 코드

Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering

https://github.com/sEhsanTaher/Beheshti-NER

공식 코드

Beheshti-NER: Persian Named Entity Recognition Using BERT

https://github.com/sa5r/kgrp

공식 코드

Knowledge Graph Completion using Structural and Textual Embeddings

https://github.com/saattrupdan/scandeval

공식 코드

ScandEval: A Benchmark for Scandinavian Natural Language Processing

https://github.com/saccharomycetes/mllm-perceptual-limitation

공식 코드

Exploring Perceptual Limitation of Multimodal Large Language Models

https://github.com/saccharomycetes/mllms_know

공식 코드

MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs

https://github.com/saccharomycetes/text-based-traffic

공식 코드

Utilizing Background Knowledge for Robust Reasoning over Traffic Situations

https://github.com/saccharomycetes/visual_crop_zsvqa

공식 코드

Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs

https://github.com/sahaana/ember

공식 코드

Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins

https://github.com/sail-sg/cpo

공식 코드

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs

https://github.com/sail-sg/lm-random-memory-access

공식 코드

Beyond Memorization: The Challenge of Random Memory Access in Language Models

https://github.com/sail-sg/sailor-llm

공식 코드

Sailor: Open Language Models for South-East Asia

https://github.com/sail-sg/vgt

공식 코드

Video Graph Transformer for Video Question Answering

https://github.com/sailxuovo/cc-riddle

공식 코드

CC-Riddle: A Question Answering Dataset of Chinese Character Riddles

https://github.com/sakharamg/kitlm

공식 코드

KITLM: Domain-Specific Knowledge InTegration into Language Models for Question Answering

https://github.com/salanueva/CBM

공식 코드

Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answering

https://github.com/salesforce/DocNLI

공식 코드

DocNLI: A Large-scale Dataset for Document-level Natural Language Inference

https://github.com/salesforce/QAConv

공식 코드

QAConv: Question Answering on Informative Conversations

https://github.com/salesforce/UniversalFewShotNLP

공식 코드

Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start

https://github.com/salesforce/augtriever

공식 코드

AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation

https://github.com/salesforce/cove

공식 코드

Learned in Translation: Contextualized Word Vectors

https://github.com/salesforce/decaNLP

공식 코드

The Natural Language Decathlon: Multitask Learning as Question Answering

https://github.com/salesforce/lavis

공식 코드

LAVIS: A Library for Language-Vision Intelligence

https://github.com/salesforce/mpt

공식 코드

Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models

https://github.com/salesforce/nnd_evaluation

공식 코드

Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets

https://github.com/salesforce/qafacteval

공식 코드

QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization

https://github.com/salesforce/qgen

공식 코드

MixQG: Neural Question Generation with Mixed Answer Types

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