Look-Ahead Bias in Language Models

Follow this topic Ask about this topic

Latest papers

8 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

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

Oct 15, 2026J/K move · Enter open · S save

When Does "Post-Call" Begin? An Availability Contract for Earnings-Call NLP Benchmarks

Xiaoyu Ma, Kelvin J. L. Koa, Yuncong Liu, Ke-Wei Huang

National University of Singapore Asian Institute of Digital Finance Singapore

Look-Ahead Bias in Language Models Forecasting Benchmarks Financial Forecasting Financial Time Series

Open paper AskPDF arXiv

Corporate financial disclosures often unfold over time, with announcements, prepared remarks, and discussion spanning multiple high-frequency return intervals. Financial NLP benchmarks can therefore suffer from a within-event timing mismatch when the prediction target begins before the textual or audio input used by a model could be complete. Chronological train--test splits do not prevent this mismatch, because it occurs inside individual events rather than across samples. We introduce an Availability Contract, which requires a benchmark to state the input boundary, evidence for input availability, the outcome start, and the claims supported by that evidence. We apply this framework to 552 earnings calls from 24 firms. For each call, we hold the return endpoint fixed and compare the previous close, a documentary call-start proxy, and a completion proxy based on reconstructed audio end plus a stipulated processing allowance. At this baseline, moving from the call-start proxy to the completion proxy flips return signs for 9.4% of calls. Holding completion-clock cutpoints fixed, 28.3% change quintile. In an independent release-session analysis of a public earnings-call volatility benchmark, shifting before-market target windows forward by one trading session raises three-day mean squared error by 18.1-21.4% across four frozen prediction streams, while their point rankings remain unchanged. Together, the results show that labels and losses can depend materially on the declared outcome clock even when model rankings appear stable. The Availability Contract makes this assumption explicit and ties post-input claims to the available timing evidence.