Singh, A, Torrance, M ORCID: https://orcid.org/0000-0002-5305-4315 and Chukharev, E,
2025.
EyeLLM: using lookback fixations to enhance human-LLM alignment for text completion.
In:
Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications.
Association for Computational Linguistics, pp. 841-849.
ISBN 9798891762701
Abstract
Recent advances in LLMs offer new opportunities for supporting student writing, particularly through real-time, composition-level feedback. However, for such support to be effective, LLMs need to generate text completions that align with the writer’s internal representation of their developing message, a representation that is often implicit and difficult to observe. This paper investigates the use of eye-tracking data, specifically lookback fixations during pauses in text production, as a cue to this internal representation. Using eye movement data from students composing texts, we compare human-generated completions with LLM-generated completions based on prompts that either include or exclude words and sentences fixated during pauses. We find that incorporating lookback fixations enhances human-LLM alignment in generating text completions. These results provide empirical support for generating fixation-aware LLM feedback and lay the foundation for future educational tools that deliver real-time, composition-level feedback grounded in writers’ attention and cognitive processes.
Item Type: | Chapter in book |
---|---|
Description: | Paper presented at 20th Workshop on Innovative Use of NLP for Building Educational Applications, Vienna, Austria, 31 Jul-1 Aug 2025. |
Creators: | Singh, A., Torrance, M. and Chukharev, E. |
Publisher: | Association for Computational Linguistics |
Date: | 25 July 2025 |
ISBN: | 9798891762701 |
Identifiers: | Number Type 10.18653/v1/2025.bea-1.61 DOI 2477228 Other |
Divisions: | Schools > School of Social Sciences |
Record created by: | Jeremy Silvester |
Date Added: | 25 Sep 2025 15:59 |
Last Modified: | 25 Sep 2025 15:59 |
URI: | https://irep.ntu.ac.uk/id/eprint/54440 |
Actions (login required)
![]() |
Edit View |
Statistics
Views
Views per month over past year
Downloads
Downloads per month over past year