SPIN Unprocessed July 10, 2026 ai_technology research
What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness
View original on arxiv.orgOverview
arXiv:2607.08046v1 Announce Type: new Abstract: Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast. We ask whether internal representations offer a more direct window into both. Working with Eternis-Forecaster 8B on OpenForesight, we train representation-pooling probes on intermediate activations and find they achieve substantially better calibration; a result
SpinGraph analysis pending — check back after processing.
Ask AI about this story
Opens with the SpinGraph .md URL and structured context — one click, prompt included.
More from arXiv Computation and Language
View all →- COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation
- MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction
- COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation
- Holographic Neural PCFG for Unsupervised Parsing
- PLURAL: A Global Dataset for Value Alignment
- Structured Pruning of Large Language Models via Power Transformation and Sign-Preserving Score Aggregation with Adaptive Feature Retention
Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO