Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models
Open accessAbstract
Explaining stock predictions is generally a difficult task for traditional non-generative deep learning models, where explanations are limited to visualizing the attention weights on important texts. Today, Large Language Models (LLMs) present a solution to this problem, given their known capabilities to generate human-readable explanations for their decision-making process. However, the task of stock prediction remains challenging for LLMs, as it requires the ability to weigh the varying impacts of chaotic social texts on stock prices. The problem gets progressively harder with the introduction of the explanation component, which requires LLMs to explain verbally why certain factors are more important than the others. On the other hand, to fine-tune LLMs for such a task, one would need expert-annotated samples of explanation for every stock movement in the training set, which is expensive and impractical to scale.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
SEP is the only work reviewed that incorporates real-time social media data in an LLM trading agent.
“However, SEP [19] is the only work we've reviewed that incorporates real-time social media data in LLM trading agent.”
From Large Language Model Agent in Financial Trading: A Survey (2026) · cites this paper as [19]
Section 3.1.2 (p. 3) says SEP uses tweets collected through the Twitter API as inputs for stock predictions. It describes a dataset from 2020–2022, not a real-time social-media feed. The source also cannot establish the citing authors’ comparison with every other work they reviewed. (LLM, conf=0.86)
Experimental — accuracy not yet measuredMost studies apply LLMs through in-context learning without any fine-tuning, with only [19] tuning the LLM during training.
“Additionally, our review reveals that most studies applies LLMs through in-context learning without any fine-tuning, with only [19] tunes the LLM during training.”
From Large Language Model Agent in Financial Trading: A Survey (2026) · cites this paper as [19]
SEP proposed leveraging reinforcement learning with memorization and reflection modules in trading agents.
“SEP [19] has proposed leveraging reinforcement learning with memorization and reflection modules in trading agents.”
From Large Language Model Agent in Financial Trading: A Survey (2026) · cites this paper as [19]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 24 · Cited by 47
This paper’s reference list could not be split into single entries.
- Authors
- Koa, K. J. L., Ma, Y., Ng, R., & Chua, T.-S.
- Affiliations
- National University of Singapore (SG)
- Eastspring Investments, Singapore, Singapore
- Venue
- Proceedings of the ACM Web Conference 2024
- Publisher
- ACM
- Published
- 2024-05-13
- Pages
- 4304-4315
- OpenAlex
- W4396757543
- Cited by
- 47
- References
- 24
- Citations by year
- 2026: 18 · 2025: 20 · 2024: 9
- FWCI
- 32.14
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- International World Wide Web Conference (WWW) (publishedVersion, cc-by)
- RePEc: Research Papers in Economics (submittedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- Singapore Management University Institutional Knowledge (InK) (Singapore Management University) (submittedVersion, other-oa)
- arXiv (Cornell University) (cc-by)
- Funders
- National Research Foundation
- National University of Singapore
- National Research Foundation Singapore
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- stock price prediction, explainable AI, large language models, social media text, stock prices, financial forecasting
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
