Saved in:
Bibliographic Details
Main Authors: Sun, Zhongtian, Xiao, Chenghao, Harit, Anoushka, Yu, Jongmin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.00205
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916981803843584
author Sun, Zhongtian
Xiao, Chenghao
Harit, Anoushka
Yu, Jongmin
author_facet Sun, Zhongtian
Xiao, Chenghao
Harit, Anoushka
Yu, Jongmin
contents Financial news is essential for accurate market prediction, but evolving narratives across macroeconomic regimes introduce semantic and causal drift that weaken model reliability. We present an evaluation framework to quantify robustness in financial NLP under regime shifts. The framework defines four metrics: (1) Financial Causal Attribution Score (FCAS) for alignment with causal cues, (2) Patent Cliff Sensitivity (PCS) for sensitivity to semantic perturbations, (3) Temporal Semantic Volatility (TSV) for drift in latent text representations, and (4) NLI-based Logical Consistency Score (NLICS) for entailment coherence. Applied to LSTM and Transformer models across four economic periods (pre-COVID, COVID, post-COVID, and rate hike), the metrics reveal performance degradation during crises. Semantic volatility and Jensen-Shannon divergence correlate with prediction error. Transformers are more affected by drift, while feature-enhanced variants improve generalisation. A GPT-4 case study confirms that alignment-aware models better preserve causal and logical consistency. The framework supports auditability, stress testing, and adaptive retraining in financial AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00205
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantifying Semantic Shift in Financial NLP: Robust Metrics for Market Prediction Stability
Sun, Zhongtian
Xiao, Chenghao
Harit, Anoushka
Yu, Jongmin
Computational Finance
Financial news is essential for accurate market prediction, but evolving narratives across macroeconomic regimes introduce semantic and causal drift that weaken model reliability. We present an evaluation framework to quantify robustness in financial NLP under regime shifts. The framework defines four metrics: (1) Financial Causal Attribution Score (FCAS) for alignment with causal cues, (2) Patent Cliff Sensitivity (PCS) for sensitivity to semantic perturbations, (3) Temporal Semantic Volatility (TSV) for drift in latent text representations, and (4) NLI-based Logical Consistency Score (NLICS) for entailment coherence. Applied to LSTM and Transformer models across four economic periods (pre-COVID, COVID, post-COVID, and rate hike), the metrics reveal performance degradation during crises. Semantic volatility and Jensen-Shannon divergence correlate with prediction error. Transformers are more affected by drift, while feature-enhanced variants improve generalisation. A GPT-4 case study confirms that alignment-aware models better preserve causal and logical consistency. The framework supports auditability, stress testing, and adaptive retraining in financial AI systems.
title Quantifying Semantic Shift in Financial NLP: Robust Metrics for Market Prediction Stability
topic Computational Finance
url https://arxiv.org/abs/2510.00205