WikiHint: A Human-Annotated Dataset for Hint Ranking and Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913800652849152 |
|---|---|
| author | Mozafari, Jamshid Gerhold, Florian Jatowt, Adam |
| author_facet | Mozafari, Jamshid Gerhold, Florian Jatowt, Adam |
| contents | The use of Large Language Models (LLMs) has increased significantly with users frequently asking questions to chatbots. In the time when information is readily accessible, it is crucial to stimulate and preserve human cognitive abilities and maintain strong reasoning skills. This paper addresses such challenges by promoting the use of hints as an alternative or a supplement to direct answers. We first introduce a manually constructed hint dataset, WikiHint, which is based on Wikipedia and includes 5,000 hints created for 1,000 questions. We then finetune open-source LLMs for hint generation in answer-aware and answer-agnostic contexts. We assess the effectiveness of the hints with human participants who answer questions with and without the aid of hints. Additionally, we introduce a lightweight evaluation method, HintRank, to evaluate and rank hints in both answer-aware and answer-agnostic settings. Our findings show that (a) the dataset helps generate more effective hints, (b) including answer information along with questions generally improves the quality of generated hints, and (c) encoder-based models perform better than decoder-based models in hint ranking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01626 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WikiHint: A Human-Annotated Dataset for Hint Ranking and Generation Mozafari, Jamshid Gerhold, Florian Jatowt, Adam Computation and Language Information Retrieval The use of Large Language Models (LLMs) has increased significantly with users frequently asking questions to chatbots. In the time when information is readily accessible, it is crucial to stimulate and preserve human cognitive abilities and maintain strong reasoning skills. This paper addresses such challenges by promoting the use of hints as an alternative or a supplement to direct answers. We first introduce a manually constructed hint dataset, WikiHint, which is based on Wikipedia and includes 5,000 hints created for 1,000 questions. We then finetune open-source LLMs for hint generation in answer-aware and answer-agnostic contexts. We assess the effectiveness of the hints with human participants who answer questions with and without the aid of hints. Additionally, we introduce a lightweight evaluation method, HintRank, to evaluate and rank hints in both answer-aware and answer-agnostic settings. Our findings show that (a) the dataset helps generate more effective hints, (b) including answer information along with questions generally improves the quality of generated hints, and (c) encoder-based models perform better than decoder-based models in hint ranking. |
| title | WikiHint: A Human-Annotated Dataset for Hint Ranking and Generation |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2412.01626 |