Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Question: How do Large Language Models perform on the Question Answering tasks? Answer (2024)
LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models (2024)
Perspective Transition of Large Language Models for Solving Subjective Tasks (2025)
Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries (2024)
Hybrid Graphs for Table-and-Text based Question Answering using LLMs (2025)
ReasVQA: Advancing VideoQA with Imperfect Reasoning Process (2025)
Probing Large Language Models in Reasoning and Translating Complex Linguistic Puzzles (2025)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2025-02-11T01:34:55.097Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7418224215507507},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}},{"id":"67ace2aa8ea95c8850988760","author":{"_id":"64510a21f800611f94f0d9f8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64510a21f800611f94f0d9f8/uB0uM3zxoiytcgAuJgfQR.jpeg","fullname":"Yuwei Yin","name":"yuweiyin","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false},"createdAt":"2025-02-12T18:04:26.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"ARR source code is now available on GitHub 🌟\nhttps://github.com/YuweiYin/ARR","html":"

ARR source code is now available on GitHub 🌟
https://github.com/YuweiYin/ARR

\n","updatedAt":"2025-02-12T18:04:26.266Z","author":{"_id":"64510a21f800611f94f0d9f8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64510a21f800611f94f0d9f8/uB0uM3zxoiytcgAuJgfQR.jpeg","fullname":"Yuwei Yin","name":"yuweiyin","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7976105809211731},"editors":["yuweiyin"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64510a21f800611f94f0d9f8/uB0uM3zxoiytcgAuJgfQR.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2502.04689","authors":[{"_id":"67a9b911b1f5eece682d7961","user":{"_id":"64510a21f800611f94f0d9f8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64510a21f800611f94f0d9f8/uB0uM3zxoiytcgAuJgfQR.jpeg","isPro":false,"fullname":"Yuwei Yin","user":"yuweiyin","type":"user"},"name":"Yuwei Yin","status":"claimed_verified","statusLastChangedAt":"2025-02-10T09:49:32.672Z","hidden":false},{"_id":"67a9b911b1f5eece682d7962","name":"Giuseppe Carenini","hidden":false}],"publishedAt":"2025-02-07T06:30:33.000Z","submittedOnDailyAt":"2025-02-10T06:00:51.974Z","title":"ARR: Question Answering with Large Language Models via Analyzing,\n Retrieving, and Reasoning","submittedOnDailyBy":{"_id":"64510a21f800611f94f0d9f8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64510a21f800611f94f0d9f8/uB0uM3zxoiytcgAuJgfQR.jpeg","isPro":false,"fullname":"Yuwei Yin","user":"yuweiyin","type":"user"},"summary":"Large language models (LLMs) achieve remarkable performance on challenging\nbenchmarks that are often structured as multiple-choice question-answering (QA)\ntasks. Zero-shot Chain-of-Thought (CoT) prompting enhances reasoning in LLMs\nbut provides only vague and generic guidance (\"think step by step\"). This paper\nintroduces ARR, an intuitive and effective zero-shot prompting method that\nexplicitly incorporates three key steps in QA solving: analyzing the intent of\nthe question, retrieving relevant information, and reasoning step by step.\nComprehensive experiments across diverse and challenging QA tasks demonstrate\nthat ARR consistently improves the Baseline (without ARR prompting) and\noutperforms CoT. Ablation and case studies further validate the positive\ncontributions of each component: analyzing, retrieving, and reasoning. Notably,\nintent analysis plays a vital role in ARR. Additionally, extensive evaluations\nacross various model sizes, LLM series, and generation settings solidify the\neffectiveness, robustness, and generalizability of ARR.","upvotes":8,"discussionId":"67a9b911b1f5eece682d798c","projectPage":"https://www.yuweiyin.com/publication/2025-02-07-arr/","githubRepo":"https://github.com/YuweiYin/ARR","githubRepoAddedBy":"user","ai_summary":"ARR, a zero-shot prompting method for question-answering tasks, incorporates intent analysis, retrieval, and reasoning to enhance performance beyond zero-shot Chain-of-Thought prompting.","ai_keywords":["Large language models","zero-shot Chain-of-Thought","zero-shot prompting","intent analysis","retrieval","reasoning","question-answering","comprehensive experiments","ablation studies","case studies","model sizes","LLM series","generation settings"],"githubStars":9,"organization":{"_id":"67481e994bcfe97d0e7f242d","name":"UBC-V","fullname":"University of British Columbia","avatar":"https://cdn-uploads.huggingface.co/production/uploads/66c75a8a060b6c3335d28ee7/5qUvu4_6J60ULUQaMYZ2C.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64510a21f800611f94f0d9f8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64510a21f800611f94f0d9f8/uB0uM3zxoiytcgAuJgfQR.jpeg","isPro":false,"fullname":"Yuwei Yin","user":"yuweiyin","type":"user"},{"_id":"66f612b934b8ac9ffa44f084","avatarUrl":"/avatars/6836c122e19c66c90f1673f28b30d7f0.svg","isPro":false,"fullname":"Tang","user":"tommysally","type":"user"},{"_id":"60078446e55258e41786a959","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60078446e55258e41786a959/UGPCE4YqG9BVMSf0YauxL.png","isPro":false,"fullname":"Motoki Wu","user":"tokestermw","type":"user"},{"_id":"64c1c77c245c55a21c6f5a13","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64c1c77c245c55a21c6f5a13/d9zlSksf3TxWpBbb-r0fd.jpeg","isPro":false,"fullname":"Reza Sayar","user":"Reza2kn","type":"user"},{"_id":"63082bb7bc0a2a5ee2253523","avatarUrl":"/avatars/6cf8d12d16d15db1070fbea89b5b3967.svg","isPro":false,"fullname":"Kuo-Hsin Tu","user":"dapumptu","type":"user"},{"_id":"64d4615cf8082bf19b916492","avatarUrl":"/avatars/8e1b59565ec5e4b31090cf1b911781b9.svg","isPro":false,"fullname":"wongyukim","user":"wongyukim","type":"user"},{"_id":"6409f386f3dabf93824bdcd2","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6409f386f3dabf93824bdcd2/4OsM9ur7C65QRDYPUuD4I.jpeg","isPro":false,"fullname":"Ougrid Dumdang","user":"Ougrid-D","type":"user"},{"_id":"65025370b6595dc45c397340","avatarUrl":"/avatars/9469599b176034548042922c0afa7051.svg","isPro":false,"fullname":"J C","user":"dark-pen","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0,"organization":{"_id":"67481e994bcfe97d0e7f242d","name":"UBC-V","fullname":"University of British Columbia","avatar":"https://cdn-uploads.huggingface.co/production/uploads/66c75a8a060b6c3335d28ee7/5qUvu4_6J60ULUQaMYZ2C.png"}}">

Papers

arxiv:2502.04689

ARR: Question Answering with Large Language Models via Analyzing, Retrieving, and Reasoning

Published on Feb 7, 2025

· Submitted by

Yuwei Yin on Feb 10, 2025

University of British Columbia

Upvote

Authors:

Yuwei Yin ,

Abstract

ARR, a zero-shot prompting method for question-answering tasks, incorporates intent analysis, retrieval, and reasoning to enhance performance beyond zero-shot Chain-of-Thought prompting.

AI-generated summary

Large language models (LLMs) achieve remarkable performance on challenging benchmarks that are often structured as multiple-choice question-answering (QA) tasks. Zero-shot Chain-of-Thought (CoT) prompting enhances reasoning in LLMs but provides only vague and generic guidance ("think step by step"). This paper introduces ARR, an intuitive and effective zero-shot prompting method that explicitly incorporates three key steps in QA solving: analyzing the intent of the question, retrieving relevant information, and reasoning step by step. Comprehensive experiments across diverse and challenging QA tasks demonstrate that ARR consistently improves the Baseline (without ARR prompting) and outperforms CoT. Ablation and case studies further validate the positive contributions of each component: analyzing, retrieving, and reasoning. Notably, intent analysis plays a vital role in ARR. Additionally, extensive evaluations across various model sizes, LLM series, and generation settings solidify the effectiveness, robustness, and generalizability of ARR.