Using LLMs for Explainable, Data-Driven Insight Generation from Time Series

Ria Mundhra G. S. dos Santos Michael Benedikt

Jun 2026 · arXiv.org · Vol abs/2607.18271 · 0 citations · 68 references

Computer Science

TL;DR

Results show that generated explanations approached analyst-written explanations in terms of readability, consistency and persuasiveness, demonstrating that grounded explanation generation for time series forecasting can be achieved at scale without domain-specific fine-tuning.

Abstract

Time series forecasts are widely used in decision-critical domains, where they are rarely consumed without accompanying explanations. Producing such explanations is usually a manual and costly process, and attempts to automate it using large language models often suffer from hallucination when applied to temporal data. We propose a domain-agnostic framework for grounded natural language explanation generation for time series forecasts, illustrated in Figure 1. The framework consists of three components: (i) extraction of structured explanatory factors from historical analyst-written explanations, (ii) evidence-conditioned explanation generation, and (iii) scalable evaluation for readability, logical consistency, and persuasiveness. The design explicitly constrains generation to verifiable evidence, reducing unsupported claims. We evaluate the framework on a financial forecasting case study involving the NASDAQ-100 index and a freight pricing case study using data from Vortexa. Results show that generated explanations approached analyst-written explanations in terms of readability, consistency and persuasiveness. These findings demonstrate that grounded explanation generation for time series forecasting can be achieved at scale without domain-specific fine-tuning.

DOI arXiv Semantic Scholar

View source

Similar papers

Preprint Aug 2026

ReasonCast: Towards Explainable Time Series Forecasting with Reasoning

ReasonCast, the recipe for finetuning any LLM to perform both tasks jointly, yields a model that generates a reasoning chain and a forecast together in a single autoregressive pass, and Extensive experiments show that ReasonCast outperforms both LLMs and TS models on prediction accuracy while producing verifiable, caus...

Seung-Han Lee, Jun Seo, Jaehoon Lee et al. · 0 citations

Preprint Aug 2026

Towards A Unified Information Bottleneck Framework for Time Series Explanations

A unified objective function for explainable time series learning that bridges attribution and counterfactual reasoning within a single framework is proposed and a novel explanation framework is introduced that learns a parametric transformation network to construct explanation-embedded instances.

Xu Zheng, Zichuan Liu, Zhuo-Min Chen et al. · 0 citations

Jul 2026

Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

IB-Forecast is proposed, an inherently interpretable multivariate time-series forecasting framework that decomposes forecasting into a learned periodic component and a residual component computed with explainable masks over input tokens that guarantees high explanation fidelity.

Xu Zheng, Wei Cheng, Zhuomin Chen et al. · arXiv.org · 2 citations

Preprint Aug 2026

When Text and Numbers Disagree: Evidence Arbitration in Large Language Models

It is suggested that current LLMs often rely on heuristic arbitration strategies when integrating heterogeneous evidence, highlighting a failure mode for tool-augmented decision systems.

Mattia Carletti, Edward Phillips, Fredrik K. Gustafsson et al. · 0 citations

Jul 2026

Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity

Inspired by Pearl's counterfactual notion of necessity, TimePNS assesses whether a temporal factor is necessary by intervening on it and measuring whether the original prediction is disrupted, and consistently improves sufficiency-necessity trade-offs over strong baselines.

Hongnan Ma, Yi-Wei Shi, Meng-Yue Yang et al. · arXiv.org · 0 citations

#small language model Preprint Aug 2026

Communicating Credit Risk with Large Language Models: Evaluation of Explanations from Standard and Alternative Data-Based Models

This work examines whether Large Language Models (LLMs) can serve as explanation layers that translate post-hoc explanation artefacts into stakeholder-appropriate risk narratives and discusses implications for the governance of risk models, including deployment considerations and the value of domain-aligned LLMs in reg...

Sahab Zandi, Noah Kostesku, Christophe Mues et al. · 0 citations