Do Language Models Update their Forecasts with New Information?
cs.CL
Submitted: 2025-09-28
Updated: 2026-09-04
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Approaching Human-Level Forecasting with Language Models
- ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data
- ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities
- Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
- Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?
- Time-R1: Towards Comprehensive Temporal Reasoning in LLMs
- Qwen2.5-VL Technical Report
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Evaluating Large Language Models: A Comprehensive Survey
- Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
- MIRAI: Evaluating LLM Agents for Event Forecasting
- PRobELM: Plausibility Ranking Evaluation for Language Models
- FOReCAst: The Future Outcome Reasoning and Confidence Assessment Benchmark
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering