Look-Ahead Bias in Language Models

Follow this topic Ask about this topic

Latest papers

12 papers4 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Thinking Fast, Trading Late: System One Decision Models vs the Market
Nov 2, 2026Amir Dehkordi, Alireza Kargarzadeh, Nariman Khaledian +3Financial Reasoning in Language Models Look-Ahead Bias in Language Models
Independent Researcher · TailState Intelligence Ltd · Zanista AI Ltd +1
Do Earnings Calls Help Predict Financial Restatements? Evaluating Text Beyond Public Firm Information
Oct 31, 2026Ahmet Efe, Shivank Sapra, Bilal AhmedFinancial Forecasting Financial Sentiment Analysis
University of Minnesota, Minneapolis, MN, USA
Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
Oct 28, 2026Huangfei Jiang, Anning Hu, Kai Sheng +7Financial Reasoning Benchmarks AI Agent Evaluation
Prophetlab · RethinkLab · Antai College of Economics and Management, SJTU +3
Beyond Causal Masks: Auditing and Localizing Hidden Future-Token Leakage in Adaptive Sequence Models
Oct 22, 2026Huiting Liu, Jinsong WuLook-Ahead Bias in Language Models LLM Auditing
Department of Electrical Engineering, University of Chile, Santiago, 8370451, Chile
When Does "Post-Call" Begin? An Availability Contract for Earnings-Call NLP Benchmarks
Oct 15, 2026Xiaoyu Ma, Kelvin J. L. Koa, Yuncong Liu +1Look-Ahead Bias in Language Models Forecasting Benchmarks
National University of Singapore Asian Institute of Digital Finance Singapore
FIDES: A Concordance Protocol for LLM-Generated Trading Strategies
Aug 24, 2026Arther Tian, Alex Ding, Simon Wu +1Look-Ahead Bias in Language Models Language Model Generation Evaluation
DGrid AI
OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents
Aug 6, 2026Xinying Cai, Minghao Guo, Jiahe Liu +7LLM Auditing Look-Ahead Bias in Language Models
Rutgers University · Technical University of Denmark · New Jersey Institute of Technology +4
Forecasting With LLMs: Improved Generalization Through Feature Steering
Jun 25, 2026Humzah Merchant, Bradford LevyLook-Ahead Bias in Language Models LLM Interpretability
University of Chicago, Illinois, United States.
Leakage-Aware Benchmarking of LLM Forecasting: Real-Time Nowcasts as the Decision-Time Input for Macro Factor Ranking
Jun 21, 2026Mao Guan, Qian ChenLearning to Rank Look-Ahead Bias in Language Models
Independent Researcher.
Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Models
May 23, 2026Weixian Waylon Li, Mengyu Wang, Tiejun MaLanguage Model Decoding Quantitative Finance
University of Edinburgh
DatedGPT: Preventing Lookahead Bias in Large Language Models with Time-Aware Pretraining
Mar 12, 2026Yutong Yan, Raphael Tang, Zhenyu Gao +2Look-Ahead Bias in Language Models Language Model Pretraining
Department of Finance, CUHK Business School, The Chinese University of Hong Kong · Centre for Artificial Intelligence, University College London
A Fast and Effective Solution to the Problem of Look-ahead Bias in LLMs
Dec 7, 2025Humzah Merchant, Bradford LevyLook-Ahead Bias in Language Models LLM-Based Time Series Forecasting
University of Chicago Chicago, IL 60637

Nov 2, 2026J/K move · Enter open · S save

Thinking Fast, Trading Late: System One Decision Models vs the Market

Amir Dehkordi, Alireza Kargarzadeh, Nariman Khaledian, Navid Parvini+2

Independent Researcher · TailState Intelligence Ltd · Zanista AI Ltd+1

Financial Reasoning in Language Models Look-Ahead Bias in Language Models LLM Auditing Time Series Forecasting

Open paper AskPDF arXiv

Large language models (LLMs) read company news at scale, and backtests suggest that their readings predict stock returns. We ask how much of that predictability survives a test that rules out look-ahead, memorization and selection. We propose OLIVIA, a protocol for such tests: point-in-time inputs with company identities masked, selection on validation data only, an analysis plan frozen by cryptographic hash, and a test period unblinded once through a logged lock. We apply it to AI decision models, non-generative language models that return probabilities for typed questions, reading news about S&P 500 stocks: an open-weights model we fine-tuned on 2024-2025 data, three commercial models and standard baselines. The fine-tuned model's signal replicated on two validation quarters (daily information coefficients 0.055 and 0.065) but fell to 0.020 (t = 1.7) on the blinded January-July 2026 test. The commercial models' readings line up with the overnight move to the open (information coefficient 0.074 to 0.077) but not with the move after it, so the news is priced by the time a trader can act on it at the open. No model can tell over- from under-reaction, and no pre-registered strategy survives costs and a deflated Sharpe ratio. Commercial models identify masked companies in 62% to 74% of cases against a 28% baseline: masking hides names, not companies. The market reads the news first.