Papers with Code 아카이브

Long Form Question Answering

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

Long-form question answering is a task requiring elaborate and in-depth answers to open-ended questions.

코드

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

https://github.com/2015aroras/calmqa

공식 코드

CaLMQA: Exploring culturally specific long-form question answering across 23 languages

https://github.com/3244we/question-rewriter

공식 코드

Putting People in LLMs' Shoes: Generating Better Answers via Question Rewriter

https://github.com/FBzzh/CACDD

공식 코드

A Claim Decomposition Benchmark for Long-form Answer Verification

https://github.com/IBM/document2slides

공식 코드

D2S: Document-to-Slide Generation Via Query-Based Text Summarization

https://github.com/THUDM/InversePrompting

공식 코드

Controllable Generation from Pre-trained Language Models via Inverse Prompting

https://github.com/WorldHellow/mHallucinations-LLM

공식 코드

How Much Do LLMs Hallucinate across Languages? On Multilingual Estimation of LLM Hallucination in the Wild

https://github.com/ZHZisZZ/modpo

공식 코드

Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization

https://github.com/acpotluri/lfqa_summary

공식 코드

Concise Answers to Complex Questions: Summarization of Long-form Answers

https://github.com/akoksal/longform

공식 코드

LongForm: Effective Instruction Tuning with Reverse Instructions

https://github.com/bugtig6351/lfqa_evaluation

공식 코드

An Empirical Study of Evaluating Long-form Question Answering

https://github.com/carriex/lfqa_eval

공식 코드

A Critical Evaluation of Evaluations for Long-form Question Answering

https://github.com/dmis-lab/olaph

공식 코드

OLAPH: Improving Factuality in Biomedical Long-form Question Answering

https://github.com/eranhirs/sentence_union_generation

공식 코드

Revisiting Sentence Union Generation as a Testbed for Text Consolidation

https://github.com/facebookresearch/ELI5

공식 코드

ELI5: Long Form Question Answering

https://github.com/google-research-datasets/quotesum

공식 코드

SEMQA: Semi-Extractive Multi-Source Question Answering

https://github.com/halfrot/ALaRM

공식 코드

ALaRM: Align Language Models via Hierarchical Rewards Modeling

https://github.com/jingfengsteven/acpo

공식 코드

Atomic Consistency Preference Optimization for Long-Form Question Answering

https://github.com/jvladika/ContextRAG

공식 코드

On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems

https://github.com/lovodkin93/attribute-first-then-generate

공식 코드

Attribute First, then Generate: Locally-attributable Grounded Text Generation

https://github.com/martiansideofthemoon/hurdles-longform-qa

공식 코드

Hurdles to Progress in Long-form Question Answering

https://github.com/meetdavidwan/generationprograms

공식 코드

GenerationPrograms: Fine-grained Attribution with Executable Programs

https://github.com/open-compass/anah

공식 코드

ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models

https://github.com/primeqa/clapnq

공식 코드

CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems

https://github.com/priyankamandikal/vedantany-10m

공식 코드

Ancient Wisdom, Modern Tools: Exploring Retrieval-Augmented LLMs for Ancient Indian Philosophy

https://github.com/swaroop-nath/rl-qfs

공식 코드

Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement Learning

https://github.com/thunlp/webcpm

공식 코드

WebCPM: Interactive Web Search for Chinese Long-form Question Answering

https://github.com/ukplab/arxiv2024-lfqa-hallucination

공식 코드

Localizing and Mitigating Errors in Long-form Question Answering

https://github.com/voidism/selfcite

공식 코드

SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models

https://github.com/xsc1234/search-in-the-chain

공식 코드

Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks

https://github.com/yangrui525/kg-rank

공식 코드

KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques

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