---
title: "MIT News | LLMs Grow an Internal Model of Reality as Language Ability Improves"
author: "Unique Research"
sourcePublication: "Unique Research (FFCAP English library)"
originalPublishedAt: "2024-08-23T17:30:00+08:00"
canonical: "https://ffcap.cn/en/research/20240823a07kay00"
source: "https://ffcap.cn/en/research/20240823a07kay00"
language: "en"
cnSourceUrl: "https://view.inews.qq.com/a/20240823A07KAY00"
---

# MIT News | LLMs Grow an Internal Model of Reality as Language Ability Improves

_Unique Research · Insight / Digest · August 23, 2024 · Source: Alex Shipps | MIT CSAIL; Charles Jin, Martin Rinard_

In controlled experiments, MIT CSAIL researchers find that language models can develop an internal simulation of reality to improve generation — suggesting future LLMs may understand language more deeply than today.

Ask GPT-4 to smell a rain-soaked campsite and it declines; ask it to _describe_ the smell and it paints “air thick with anticipation” and “fresh yet earthy” — with neither rain experience nor a nose. One story: pure text imitation. Another: something closer to understanding (e.g., that a lion is “larger” than a house cat) without eyes.

## Karel puzzles + probing

The team built small **Karel** puzzles — writing instructions for a robot in a simulated grid — trained an LLM _without_ showing how solutions actually work, then used **probing** to inspect the model’s “thought process” while generating new solutions. After training on **\>1M** random puzzles, the model spontaneously formed concepts of the underlying simulation — despite never seeing that reality in training. That challenges intuitions about what information is required to learn linguistic meaning.

Probing let **Charles Jin** watch progress: the model internally simulated how the robot responds to each instruction. As puzzle-solving improved, those concepts grew more accurate; the model began assembling valid instruction sequences. Stages resemble child language: babble → grammar that looks right but fails → meaning that implements the spec.

## The “odd world” control

Risk: the probe might do some of the thinking — decoding syntax into robot motion without the LLM encoding meaning. Researchers flipped instruction meanings for a new probe (“up” means “down” in an “odd world”). If the probe only translated instructions, it should still map odd meanings; if it was reading robot-motion encodings from the LLM’s process, odd meanings should fail. The new probe erred — original semantics lived in the language model, independent of the first classifier.

Senior author **Martin Rinard** (MIT EECS / CSAIL): the work hits a core question — are LLM feats only mass statistical correlation, or do models build meaningful models of the reality they process? Here an LLM developed an internal model of a simulated reality without being trained to do so.

## Limits and open questions

Caveats: very simple programming language; relatively small model; broader settings planned. The paper does not prescribe how to accelerate meaning learning, but may inform training. Rinard: whether LLMs _use_ that internal model to reason about the real world and solve robot navigation remains open — results are consistent with use, but experiments were not designed to answer it.

_Original: Alex Shipps | MIT CSAIL._

— END —

---

Editorial English edition published on UniqueCapital: https://ffcap.cn/en/research/20240823a07kay00
On-site reading page: https://ffcap.cn/en/research/20240823a07kay00