Preprint

TIEM: Temporal Integration of Hypergraph Evidence and Skill Memory for Event-Driven Financial Forecasting

Wen-Jin Liu Shengjie Pang Chen-Xi Wang Tiesunlong Shen Jia-Jie He Zhe Cui Xiao-Bao Wu A. Lưu Hao-Ran Luo

Aug 2026 · 1 citation · 48 references

Computer Science

TL;DR

TIEM, a timestamp-gated framework with three coordinated components: an Event-Evidence Hypergraph (EEH) for timestamp-filtered multi-tier retrieval; a Case-based Skill Memory (CSM) for source-tagged temporal skills; and Heterogeneous Evidence-Experience Fusion Reasoning (HEFR) for evidence-experience fusion and prediction.

Abstract

Event-driven catalyst-outcome forecasting increasingly uses retrieval- and memory-augmented large language model agents for prediction. However, training-data contamination and temporal leakage can create an Evidence Chasm between reported accuracy and true predictive ability. We propose TIEM, a timestamp-gated framework with three coordinated components: an Event-Evidence Hypergraph (EEH) for timestamp-filtered multi-tier retrieval; a Case-based Skill Memory (CSM) for source-tagged temporal skills; and Heterogeneous Evidence-Experience Fusion Reasoning (HEFR) for evidence-experience fusion and prediction. We also introduce FinPURE, a recent-period A-share holdout benchmark, and use a Name-Date Probe to assess per-model name-date sensitivity rather than assuming training cutoffs. Results on five financial forecasting benchmarks show TIEM outperforms current baselines. Our project is available at https://github.com/QwenQKing/Fin_TIEM.

arXiv Semantic Scholar

View source

Similar papers

#small language model Review Aug 2026

LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications

This work investigates LLM-based forecasting agents, meaning systems in which a language model contributes to a scored prediction about a future or currently unobserved target, and organizes architectures into three groups.

Xiao-Gang Xu, Jiaqi Tang, Jianmin Chen et al. · 0 citations

Preprint Aug 2026

REATS: LLM Reasoning-based Ensemble Learning for Adaptive Time Series Forecasting

REATS is proposed, which leverages LLM reasoning capabilities as an intelligent ensemble router that jointly processes textual temporal pattern descriptions and numerical features to produce interpretable, sample-adaptive ensemble weights through chain-of-thought reasoning.

Xu Zhang, Chang Xu, Hui Sun et al. · 0 citations

Jul 2026

CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation

This work proposes the method, a model-agnostic framework for long-horizon recommendation, which uses a frozen multimodal language model to convert item content and feedback into evidence-grounded semantic atoms, then maintains separate short-term, long-term, and exposure memories.

Gengyu Zhan · arXiv.org · 0 citations

Jul 2026

ReDiTT: Retrieval Augmented Conditional Diffusion Transformers for Asynchronous Time Series

ReDiTT, a retrieval augmented conditional diffusion transformer that operates in latent space, is introduced, a retrieval augmented conditional diffusion transformer that operates in latent space that stabilizes long horizon forecasting and improves sample diversity.

Saiyue Lyu, Zhi-Tian Zhang, Ruizhi Deng et al. · Trans. Mach. Learn. Res. · 0 citations

Book Open access Aug 2026

Think-like-LSTM: Memory-Augmented Large Language Models via Dynamic Fine-Tuning for Financial Risk Assessment

FraLLM is a novel LLM fine-tuning framework that seamlessly internalizes transaction-oriented knowledge for FRA and introduces the Memory Token Mechanism, which recurrently aggregates historical text prototypes into a compact, continuously updated memory token that allows LLMs to effectively synthesize long-term transa...

Si-Wei Zhang, Yun Xiong, Xi Chen et al. · Proceedings of the 32nd ACM... · 1 citation

Open access 2026

A Data Stream Approach to Predicting Risk: An Incremental Learning Model

An incremental recurrent learning framework for adverse-event count prediction is developed and evaluated in a field study of human-social-infrastructure projects in Afghanistan and demonstrates that incremental recurrent learning can support adaptive risk monitoring when adverse-event distributions change over time.

Donghui Shi, Ji-Fei Cheng, Ya-Kun Sun et al. · IEEE Access · 0 citations