mlsanityData to 7 Oct 2026

STRUX: An LLM for Decision-Making with Structured Explanations

arXiv 2410.12583 ↗First posted 16 Oct 2024cs.CL cs.AIcited by 7

Not on the map. Why?

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.

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

Builds on

19 of 40 references.

References · 19

  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  2. 2023Towards Understanding Sycophancy in Language Modelscited by 988
  3. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
  4. 2022Complementary Explanations for Effective In-Context Learningcited by 71
  5. 2024DocFinQA: A Long-Context Financial Reasoning Datasetcited by 59
  6. 2024Linguistic Calibration of Long-Form Generationscited by 59
  7. 2024Determinants of LLM-assisted Decision-Makingcited by 55
  8. 2021COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentencescited by 40
  9. 2022Toward Unifying Text Segmentation and Long Document Summarizationcited by 28
  10. 2021Rationales for Sequential Predictionscited by 26
  11. 2023Explanation-based Finetuning Makes Models More Robust to Spurious Cuescited by 24
  12. 2024Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approachcited by 24
7 more
  1. 2019Modeling financial analysts' decision making via the pragmatics and semantics of earnings callscited by 17
  2. 2022Learning to Ask Like a Physiciancited by 16
  3. 2021StreamHover: Livestream Transcript Summarization and Annotationcited by 15
  4. 2022An Exploratory Study of Stock Price Movements from Earnings Callscited by 14
  5. 2024SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMscited by 8
  6. 2024When Reasoning Meets Information Aggregation: A Case Study with Sports Narrativescited by 7
  7. 2023Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 6.

7 papers.

  1. 2025LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planningcited by 6
  2. 2026From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discoverycited by 4
  3. 2026DIALECTIC: A Multi-Agent System for Startup Evaluationcited by 2
  4. 2026CONDESION-BENCH: Conditional Decision-Making of Large Language Models in Compositional Action Spacecited by 0
  5. 2026Integrating the Analytic Hierarchy Process with Large Language Models for Transparent Multi-Criteria Decision-Makingcited by 0
  6. 2026MM-FinEval: A Multi-Task Multimodal Benchmark for Real-World Financial Forecastingcited by 0
  7. 2026A Citation-Grounded Benchmark for Trustworthy Earnings Call Transcript Analysis with Large Language Modelscited by 0