# STRUX: An LLM for Decision-Making with Structured Explanations

arXiv: https://arxiv.org/abs/2410.12583 · HTML: https://mlsanity.com/paper/2410.12583/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Builds on (most cited first, 19 of 19)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [Complementary Explanations for Effective In-Context Learning](https://mlsanity.com/paper/2211.13892/) (2022)
- [DocFinQA: A Long-Context Financial Reasoning Dataset](https://mlsanity.com/paper/2401.06915/) (2024)
- [Linguistic Calibration of Long-Form Generations](https://mlsanity.com/paper/2404.00474/) (2024)
- [Determinants of LLM-assisted Decision-Making](https://mlsanity.com/paper/2402.17385/) (2024)
- [COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences](https://mlsanity.com/paper/2106.00969/) (2021)
- [Toward Unifying Text Segmentation and Long Document Summarization](https://mlsanity.com/paper/2210.16422/) (2022)
- [Rationales for Sequential Predictions](https://mlsanity.com/paper/2109.06387/) (2021)
- [Explanation-based Finetuning Makes Models More Robust to Spurious Cues](https://mlsanity.com/paper/2305.04990/) (2023)
- [Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach](https://mlsanity.com/paper/2408.06634/) (2024)
- [Modeling financial analysts' decision making via the pragmatics and semantics of earnings calls](https://mlsanity.com/paper/1906.02868/) (2019)
- [Learning to Ask Like a Physician](https://mlsanity.com/paper/2206.02696/) (2022)
- [StreamHover: Livestream Transcript Summarization and Annotation](https://mlsanity.com/paper/2109.05160/) (2021)
- [An Exploratory Study of Stock Price Movements from Earnings Calls](https://mlsanity.com/paper/2203.12460/) (2022)
- [SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs](https://mlsanity.com/paper/2402.10979/) (2024)
- [When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives](https://mlsanity.com/paper/2406.12084/) (2024)
- [Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation](https://mlsanity.com/paper/2311.09136/) (2023)

## Built on by (most cited first, 7 of 7)

- [LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning](https://mlsanity.com/paper/2507.08496/) (2025)
- [From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery](https://mlsanity.com/paper/2605.15412/) (2026)
- [DIALECTIC: A Multi-Agent System for Startup Evaluation](https://mlsanity.com/paper/2603.12274/) (2026)
- [CONDESION-BENCH: Conditional Decision-Making of Large Language Models in Compositional Action Space](https://mlsanity.com/paper/2604.09029/) (2026)
- [Integrating the Analytic Hierarchy Process with Large Language Models for Transparent Multi-Criteria Decision-Making](https://mlsanity.com/paper/2609.16779/) (2026)
- [MM-FinEval: A Multi-Task Multimodal Benchmark for Real-World Financial Forecasting](https://mlsanity.com/paper/2609.38523/) (2026)
- [A Citation-Grounded Benchmark for Trustworthy Earnings Call Transcript Analysis with Large Language Models](https://mlsanity.com/paper/2610.00969/) (2026)

## Abstract (arXiv)

Countless decisions shape our daily lives, and it is paramount to understand the how and why behind these choices. In this paper, we introduce a new LLM decision-making framework called STRUX, which enhances LLM decision-making by providing structured explanations. These include favorable and adverse facts related to the decision, along with their respective strengths. STRUX begins by distilling lengthy information into a concise table of key facts. It then employs a series of self-reflection steps to determine which of these facts are pivotal, categorizing them as either favorable or adverse in relation to a specific decision. Lastly, we fine-tune an LLM to identify and prioritize these key facts to optimize decision-making. STRUX has been evaluated on the challenging task of forecasting stock investment decisions based on earnings call transcripts and demonstrated superior performance against strong baselines. It enhances decision transparency by allowing users to understand the impact of different factors, representing a meaningful step towards practical decision-making with LLMs.