https://highlightedchainofthought.github.io/\n","updatedAt":"2025-03-06T17:48:08.857Z","author":{"_id":"639ac72e94cad09c5a16c169","avatarUrl":"/avatars/d676019ba2ccb6266791742c5a40a39e.svg","fullname":"TTN","name":"ttn0011","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":6,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.27994582056999207},"editors":["ttn0011"],"editorAvatarUrls":["/avatars/d676019ba2ccb6266791742c5a40a39e.svg"],"reactions":[],"isReport":false}},{"id":"67ca25c80f09a8eedf2a6158","author":{"_id":"639ac72e94cad09c5a16c169","avatarUrl":"/avatars/d676019ba2ccb6266791742c5a40a39e.svg","fullname":"TTN","name":"ttn0011","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":6,"isUserFollowing":false},"createdAt":"2025-03-06T22:46:32.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Modern LLMs can bold, italicize or underline their text. Why not highlight as well? We propose Highlighted Chain of Thought (HoT), a technique for prompting LLMs to generate highlights around their responses that links specific information from the user query to the LLM response. This method improves user experiences and improves answer accuracy when compared to vanilla Chain of Thought prompting.","html":"
Modern LLMs can bold, italicize or underline their text. Why not highlight as well? We propose Highlighted Chain of Thought (HoT), a technique for prompting LLMs to generate highlights around their responses that links specific information from the user query to the LLM response. This method improves user experiences and improves answer accuracy when compared to vanilla Chain of Thought prompting.
\n","updatedAt":"2025-03-06T22:46:32.872Z","author":{"_id":"639ac72e94cad09c5a16c169","avatarUrl":"/avatars/d676019ba2ccb6266791742c5a40a39e.svg","fullname":"TTN","name":"ttn0011","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":6,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8895646333694458},"editors":["ttn0011"],"editorAvatarUrls":["/avatars/d676019ba2ccb6266791742c5a40a39e.svg"],"reactions":[{"reaction":"👍","users":["loganbolton","taesiri","anhng8","sugatoray","ttn0011"],"count":5}],"isReport":false}},{"id":"67ca4d1dc8bea6b3d9c17160","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},"createdAt":"2025-03-07T01:34:21.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [ARR: Question Answering with Large Language Models via Analyzing, Retrieving, and Reasoning](https://huggingface.co/papers/2502.04689) (2025)\n* [Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language Models](https://huggingface.co/papers/2501.18645) (2025)\n* [SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models](https://huggingface.co/papers/2502.09390) (2025)\n* [Zero-Shot and Efficient Clarification Need Prediction in Conversational Search](https://huggingface.co/papers/2503.00179) (2025)\n* [Perspective Transition of Large Language Models for Solving Subjective Tasks](https://huggingface.co/papers/2501.09265) (2025)\n* [Probing Large Language Models in Reasoning and Translating Complex Linguistic Puzzles](https://huggingface.co/papers/2502.00817) (2025)\n* [Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong](https://huggingface.co/papers/2501.09775) (2025)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\nThe following papers were recommended by the Semantic Scholar API
\n- \n
- ARR: Question Answering with Large Language Models via Analyzing, Retrieving, and Reasoning (2025) \n
- Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language Models (2025) \n
- SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models (2025) \n
- Zero-Shot and Efficient Clarification Need Prediction in Conversational Search (2025) \n
- Perspective Transition of Large Language Models for Solving Subjective Tasks (2025) \n
- Probing Large Language Models in Reasoning and Translating Complex Linguistic Puzzles (2025) \n
- Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong (2025) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Dataset for HoT:
https://huggingface.co/datasets/groundingauburn/HoT
Papers
arxiv:2503.02003
HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs
Abstract
Highlighted Chain-of-Thought Prompting improves human verification of LLM responses but can lead to overconfidence in incorrect answers.
AI-generated summary
An Achilles heel of Large Language Models (LLMs) is their tendency to hallucinate non-factual statements. A response mixed of factual and non-factual statements poses a challenge for humans to verify and accurately base their decisions on. To combat this problem, we propose Highlighted Chain-of-Thought Prompting (HoT), a technique for prompting LLMs to generate responses with XML tags that ground facts to those provided in the query. That is, given an input question, LLMs would first re-format the question to add XML tags highlighting key facts, and then, generate a response with highlights over the facts referenced from the input. Interestingly, in few-shot settings, HoT outperforms vanilla chain of thought prompting (CoT) on a wide range of 17 tasks from arithmetic, reading comprehension to logical reasoning. When asking humans to verify LLM responses, highlights help time-limited participants to more accurately and efficiently recognize when LLMs are correct. Yet, surprisingly, when LLMs are wrong, HoTs tend to make users believe that an answer is correct.
Community
Modern LLMs can bold, italicize or underline their text. Why not highlight as well? We propose Highlighted Chain of Thought (HoT), a technique for prompting LLMs to generate highlights around their responses that links specific information from the user query to the LLM response. This method improves user experiences and improves answer accuracy when compared to vanilla Chain of Thought prompting.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- ARR: Question Answering with Large Language Models via Analyzing, Retrieving, and Reasoning (2025)
- Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language Models (2025)
- SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models (2025)
- Zero-Shot and Efficient Clarification Need Prediction in Conversational Search (2025)
- Perspective Transition of Large Language Models for Solving Subjective Tasks (2025)
- Probing Large Language Models in Reasoning and Translating Complex Linguistic Puzzles (2025)
- Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong (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:
@librarian-bot
recommend
This comment has been hidden
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2503.02003 in a model README.md to link it from this page.
Datasets citing this paper 2
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2503.02003 in a Space README.md to link it from this page.