From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting

• URL: http://arxiv.org/abs/2606.03097v1
• Date: Tue, 02 Jun 2026 03:36:30 GMT
• Title: From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting
• Abstract summary: We develop a novel framework that combines importance-aware news compression and process-level retrieval supervision.<n> Experiments on finance, energy, traffic, and bitcoin forecasting benchmarks show that our method improves prediction accuracy over strong baselines.
• Score: 37.31650180872261
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-based news-forecasting pipelines face two practical limitations: relevant news articles often exceed the model's context window, and iterative retrieval of supplementary news is typically unguided, leading to redundant updates and slow convergence. We address these issues with a novel framework that combines importance-aware news compression and process-level retrieval supervision. First, we train an importance reward model that estimates the forecasting utility of each article and uses this signal to allocate compression budgets during sequential pairwise fusion, preserving informative content within a fixed context limit. Second, we introduce a process reward model (PRM) that ranks multiple supplementary-news candidates conditioned on the current error profile and the history of previously selected articles, replacing one-shot blind retrieval with quality-controlled selection. Both components are trained offline using historical data with ground truth; inference uses the frozen filtering logic and compression modules without any reflection loop. Experiments on finance, energy, traffic, and bitcoin forecasting benchmarks show that our method improves prediction accuracy over strong baselines, significantly reduces the number of refinement iterations compared to the iterative baseline, and remains effective when relevant articles span thousands of tokens.

Related papers

• Reproducing Omitted Temporal Expressions in Japanese News for Retrieval-Augmented Applications [0.7448254811651419]
  News articles often contain omitted temporal expressions, which must be interpreted with reference to the publication date.<n>We focus on reproducing omitted temporal expressions as concrete dates or intervals using the publication date as external context.<n>We propose jaROTE, a rule-based pipeline for Japanese news articles.
  arXiv  Detail & Related papers  (2026-09-09T00:49:27Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• Generative Regression Based Watch Time Prediction for Short-Video Recommendation [36.95095097454143]
  Watch time prediction has emerged as a pivotal task in short video recommendation systems.<n>Recent studies have attempted to address these issues by converting the continuous watch time estimation into an ordinal regression task.<n>We propose a novel Generative Regression (GR) framework that reformulates WTP as a sequence generation task.
  arXiv  Detail & Related papers  (2024-12-28T16:48:55Z)
• From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection [16.47323362700347]
  We introduce a novel approach to enhance time series forecasting by reasoning across both text and time series data. With language as a medium, our method adaptively integrates social events into forecasting models, aligning news content with time series fluctuations to provide richer insights. Specifically, we utilize LLM-based agents to iteratively filter out irrelevant news and employ human-like reasoning to evaluate predictions.
  arXiv  Detail & Related papers  (2024-09-26T03:50:22Z)
• Interactive Test-Time Adaptation with Reliable Spatial-Temporal Voxels for Multi-Modal Segmentation [56.70910056845503]
  Multi-modal test-time adaptation (MM-TTA) adapts models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner.<n>Previous MM-TTA methods for 3D segmentation suffer from two major limitations: 1) unstable frame-wise predictions caused by temporal inconsistency, and 2) consistently incorrect predictions that violate the assumption of reliable modality guidance.<n>This work introduces a comprehensive two-fold framework: Latte++ that better suppresses the unstable frame-wise predictions with more informative geometric correspondences, and Interactive Test-Time Adaptation (ITTA), a flexible add-on to empower effortless human feedback
  arXiv  Detail & Related papers  (2024-03-11T06:56:08Z)
• AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval [9.357912396498142]
  We introduce AutoCast++, a zero-shot ranking-based context retrieval system. Our approach first re-ranks articles based on zero-shot question-passage relevance, honing in on semantically pertinent news. We conduct both the relevance evaluation and article summarization without needing domain-specific training.
  arXiv  Detail & Related papers  (2023-10-03T08:34:44Z)
• Prompt-and-Align: Prompt-Based Social Alignment for Few-Shot Fake News Detection [50.07850264495737]
  "Prompt-and-Align" (P&A) is a novel prompt-based paradigm for few-shot fake news detection. We show that P&A sets new states-of-the-art for few-shot fake news detection performance by significant margins.
  arXiv  Detail & Related papers  (2023-09-28T13:19:43Z)
• Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation [59.417443739208146]
  We propose a new event forecasting model based on a novel training framework of historical contrastive learning. CENET learns both the historical and non-historical dependency to distinguish the most potential entities. We evaluate our proposed model on five benchmark graphs.
  arXiv  Detail & Related papers  (2023-08-29T03:26:38Z)
• A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach [53.727460222955266]
  Temporal Sentence Grounding in Videos (TSGV) aims to ground a natural language sentence in an untrimmed video. Recent studies have found that current benchmark datasets may have obvious moment annotation biases. We introduce a new evaluation metric "dR@n,IoU@m" that discounts the basic recall scores to alleviate the inflating evaluation caused by biased datasets.
  arXiv  Detail & Related papers  (2022-03-10T08:58:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.