# Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect

arXiv: https://arxiv.org/abs/2607.14111 · HTML: https://mlsanity.com/paper/2607.14111/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 15 of 15)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Do Large Language Models Know What They Don't Know?](https://mlsanity.com/paper/2305.18153/) (2023)
- [Looking Inward: Language Models Can Learn About Themselves by Introspection](https://mlsanity.com/paper/2410.13787/) (2024)
- [Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs](https://mlsanity.com/paper/2407.04694/) (2024)
- [How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions](https://mlsanity.com/paper/2309.15840/) (2023)
- [Emergent Introspective Awareness in Large Language Models](https://mlsanity.com/paper/2601.01828/) (2026)
- [Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers](https://mlsanity.com/paper/2512.15674/) (2025)
- [Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants](https://mlsanity.com/paper/2512.15712/) (2025)
- [Loop as a Bridge: Can Looped Transformers Truly Link Representation Space and Natural Language Outputs?](https://mlsanity.com/paper/2601.10242/) (2026)

## Built on by (most cited first, 1 of 1)

- [A Sense of Proprioception in Language Models](https://mlsanity.com/paper/2610.17495/) (2026)

## Abstract (arXiv)

Can small language models detect and report on perturbations their own internal activations? We investigate this question through the lens of activation steering: injecting concept vectors into a model's residual stream and measuring whether the model can accurately report on the perturbation. We first show that the binary detection paradigm used in prior work -- prompting the model to answer Yes'' or No'' to whether it detects an injected thought -- is confounded in small models, as steering biases the model toward affirmative responses regardless of the question content. We therefore propose two confound-free evaluation paradigms: sentence localization (identifying which of N sentences was perturbed, chance = 1/N) and strength comparison (identifying which of two sentences received a stronger injection, chance = 50%). Evaluating across six models from two families (Llama-3.2 and Gemma-4), we find that models as small as 2B parameters introspect reliably well above chance, and that introspective ability generally increases with scale. Llama-1B, however, performs at or below chance. We then introduce Introspection Fine-Tuning (IFT): supervised fine-tuning on sentence-localization examples constructed from the model's own perturbed forward passes. IFT raises Llama-1B sentence-localization accuracy from 9.6% to 60.6% (a 6× improvement), with gains generalizing zero-shot to the held-out strength-comparison task (30.2% → 52.2%). IFT also improves introspection for 3B and 8B models, while inducing negligible degradation on standard capability benchmarks. Our results suggest that introspective ability is not fixed by scale alone: it can be directly trained, and doing so unlocks latent self-monitoring capacity with implications for AI transparency and alignment. Our code is hrefhttps://anonymous.4open.science/r/IFT-introspection-2092/README.mdhere.