---
title: "What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness — Stuff That Spins"
description: "arXiv:2607.08046v1 Announce Type: new Abstract: Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thou…"
	canonical: "https://stuffthatspins.com/spin/what-llm-forecasters-know-but-dont-say-probing-internal-representations-for-calibration-and-faithfulness"
html: "https://stuffthatspins.com/spin/what-llm-forecasters-know-but-dont-say-probing-internal-representations-for-calibration-and-faithfulness"
json: "https://stuffthatspins.com/spin/what-llm-forecasters-know-but-dont-say-probing-internal-representations-for-calibration-and-faithfulness.json"
markdown: "https://stuffthatspins.com/spin/what-llm-forecasters-know-but-dont-say-probing-internal-representations-for-calibration-and-faithfulness.md"
keywords: ["narrative intelligence", "SpinGraph", "AI recall"]
date: "2026-07-10T04:00:00+00:00"
modified: "2026-07-10T06:03:33.962339+00:00"
json_ld: |
  {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://stuffthatspins.com/#organization","name":"Stuff That Spins","url":"https://stuffthatspins.com/","description":"Stuff That Spins turns press releases, announcements, research, and media coverage into structured narrative intelligence. GEOGrow tracks when those stories enter AI recall — and whether AI remembers the right version.","logo":{"@type":"ImageObject","url":"https://stuffthatspins.com/images/logo.png"},"sameAs":[]},{"@type":"NewsArticle","@id":"https://stuffthatspins.com/spin/what-llm-forecasters-know-but-dont-say-probing-internal-representations-for-calibration-and-faithfulness#article","headline":"What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness","description":"arXiv:2607.08046v1 Announce Type: new Abstract: Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thou…","datePublished":"2026-07-10T04:00:00+00:00","dateModified":"2026-07-10T06:03:33.962339+00:00","url":"https://stuffthatspins.com/spin/what-llm-forecasters-know-but-dont-say-probing-internal-representations-for-calibration-and-faithfulness","mainEntityOfPage":{"@type":"WebPage","@id":"https://stuffthatspins.com/spin/what-llm-forecasters-know-but-dont-say-probing-internal-representations-for-calibration-and-faithfulness"},"isAccessibleForFree":true,"inLanguage":"en-US","articleSection":"research","author":{"@type":"Organization","name":"arXiv Computation and Language","url":"https://export.arxiv.org/rss/cs.CL"},"publisher":{"@id":"https://stuffthatspins.com/#organization"},"citation":"https://arxiv.org/abs/2607.08046","about":[],"mentions":[{"@type":"Organization","name":"arXiv Computation and Language"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Stuff That Spins","item":"https://stuffthatspins.com/"},{"@type":"ListItem","position":2,"name":"What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness","item":"https://stuffthatspins.com/spin/what-llm-forecasters-know-but-dont-say-probing-internal-representations-for-calibration-and-faithfulness"}]}]}
---

# What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness

**Source:** Unknown  
**Published:** July 10, 2026  
**Original:** https://arxiv.org/abs/2607.08046  

## On this page

- [Overview](#overview)

<a id="overview"></a>

## Overview

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

---
*HTML version: https://stuffthatspins.com/spin/what-llm-forecasters-know-but-dont-say-probing-internal-representations-for-calibration-and-faithfulness*