CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference
cs.LG, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/QwenQKing/Chain
Terminology
Sources
- Scaling Open-Ended Reasoning to Predict the Future
- DeepSeek-V3 Technical Report
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Automatically Labeling Clinical Trial Outcomes: A Large-Scale Benchmark for Drug Development
- GPT-4o System Card
- Future Is Unevenly Distributed: Forecasting Ability of LLMs Depends on What We're Asking
- Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impacts
- Evaluating LLMs on Real-World Forecasting Against Expert Forecasters
- Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation
- QA-Calibration of Language Model Confidence Scores
- Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs
- Event-CausNet: Unlocking Causal Knowledge from Text with Large Language Models for Reliable Spatio-Temporal Forecasting
- Consistency Checks for Language Model Forecasters
- Pitfalls in Evaluating Language Model Forecasters
- When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation
- PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation
- Future-as-Label: Scalable Supervision from Real-World Outcomes
- Bench to the Future: A Pastcasting Benchmark for Forecasting Agents
- Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks