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/francesco-sovrano/from-philosophy-to-interfaces-an-explanatory-method-and-a-tool-inspired-by-achinstein-s-theory-of-e

공식 코드

From Philosophy to Interfaces: an Explanatory Method and a Tool Inspired by Achinstein's Theory of Explanation

https://github.com/francesco-sovrano/yai4hu

공식 코드

Generating User-Centred Explanations via Illocutionary Question Answering: From Philosophy to Interfaces

https://github.com/francois-rd/accord

공식 코드

$\texttt{ACCORD}$: Closing the Commonsense Measurability Gap

https://github.com/francoisluus/KGReasoning

공식 코드

Logic Embeddings for Complex Query Answering

https://github.com/frankaging/Causal-Distill

공식 코드

Causal Distillation for Language Models

https://github.com/frankkramer-lab/ensmic

공식 코드

An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural Networks

https://github.com/freddieniu/prompt-qa

공식 코드

Learning to Generalize for Cross-domain QA

https://github.com/frederickszk/LRNet

공식 코드

Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features

https://github.com/freedomintelligence/allava

공식 코드

ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models

https://github.com/freedomintelligence/huatuo-26m

공식 코드

Huatuo-26M, a Large-scale Chinese Medical QA Dataset

https://github.com/freedomintelligence/reasoningnlp

공식 코드

Natural Language Reasoning, A Survey

https://github.com/freedomintelligence/trim

공식 코드

Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs

https://github.com/freesunshine0316/nary-grn

공식 코드

Tackling Graphical NLP problems with Graph Recurrent Networks

https://github.com/frenkie-chiang/danmakutppbench

공식 코드

DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding

https://github.com/fromm-m/aaai2021-am-peer-reviews

공식 코드

Argument Mining Driven Analysis of Peer-Reviews

https://github.com/fsoft-ai4code/xmainframe

공식 코드

XMainframe: A Large Language Model for Mainframe Modernization

https://github.com/fualsan/datwep

공식 코드

Dynamic Task and Weight Prioritization Curriculum Learning for Multimodal Imagery

https://github.com/fudandisc/disc-finllm

공식 코드

DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuning

https://github.com/fudanvi/generative-abstract-reasoning

공식 코드

Raven's Progressive Matrices Completion with Latent Gaussian Process Priors

https://github.com/fujitsuresearch/transformer_module_networks

공식 코드

Transformer Module Networks for Systematic Generalization in Visual Question Answering

https://github.com/function2-llx/mmmm

공식 코드

VividMed: Vision Language Model with Versatile Visual Grounding for Medicine

https://github.com/fuzihaofzh/band

공식 코드

BAND: Biomedical Alert News Dataset

https://github.com/fyshelab/qa-zre

공식 코드

Weakly-Supervised Questions for Zero-Shot Relation Extraction

https://github.com/fyyfu/headkv

공식 코드

Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning

https://github.com/fyyfu/safetyalignnlp

공식 코드

Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack

https://github.com/gabegrand/adversarial-vqa

공식 코드

Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects

https://github.com/gair-nlp/metacritique

공식 코드

The Critique of Critique

https://github.com/gaiyu0/cfq

공식 코드

Grounded Graph Decoding Improves Compositional Generalization in Question Answering

https://github.com/galatolofederico/cerbero-7b

공식 코드

Cerbero-7B: A Leap Forward in Language-Specific LLMs Through Enhanced Chat Corpus Generation and Evaluation

https://github.com/gameeval/gameeval

공식 코드

GameEval: Evaluating LLMs on Conversational Games

https://github.com/gankim/tree-of-clarifications

공식 코드

Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models

https://github.com/gaosx2000/sg_kbqa

공식 코드

Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation

https://github.com/garygutc/lapa_model

공식 코드

LaPA: Latent Prompt Assist Model For Medical Visual Question Answering

https://github.com/garyjiajia/ofv2_icl_vqa

공식 코드

How to Configure Good In-Context Sequence for Visual Question Answering

https://github.com/gasolsun36/apollo

공식 코드

APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning

https://github.com/gasolsun36/tog

공식 코드

Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph

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