# Trainable Transformer in Transformer

arXiv: https://arxiv.org/abs/2307.01189 · HTML: https://mlsanity.com/paper/2307.01189/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 87 references that are in the map.
- First posted on arXiv 3 Jul 2023.

## Builds on (most cited first, 30 of 60)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Transformers learn in-context by gradient descent](https://mlsanity.com/paper/2212.07677/) (2022)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [What Can Transformers Learn In-Context? A Case Study of Simple Function Classes](https://mlsanity.com/paper/2208.01066/) (2022)
- [What learning algorithm is in-context learning? Investigations with linear models](https://mlsanity.com/paper/2211.15661/) (2022)

## Built on by (most cited first, 17 of 17)

- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?](https://mlsanity.com/paper/2410.08292/) (2024)
- [Why Larger Language Models Do In-context Learning Differently?](https://mlsanity.com/paper/2405.19592/) (2024)
- [A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time](https://mlsanity.com/paper/2309.07418/) (2023)
- [The Fine-Grained Complexity of Gradient Computation for Training Large Language Models](https://mlsanity.com/paper/2402.04497/) (2024)
- [How to Protect Copyright Data in Optimization of Large Language Models?](https://mlsanity.com/paper/2308.12247/) (2023)
- [Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot](https://mlsanity.com/paper/2406.06893/) (2024)
- [Why Softmax Attention Outperforms Linear Attention](https://mlsanity.com/paper/2310.11685/) (2023)
- [Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights](https://mlsanity.com/paper/2310.12462/) (2023)
- [On the Role of Depth and Looping for In-Context Learning with Task Diversity](https://mlsanity.com/paper/2410.21698/) (2024)
- [Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression](https://mlsanity.com/paper/2311.15390/) (2023)
- [The Expressibility of Polynomial based Attention Scheme](https://mlsanity.com/paper/2310.20051/) (2023)
- [Convergence of Two-Layer Regression with Nonlinear Units](https://mlsanity.com/paper/2308.08358/) (2023)
- [A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer](https://mlsanity.com/paper/2311.13624/) (2023)
- [One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space](https://mlsanity.com/paper/2311.14652/) (2023)
- [Subquadratic Algorithms and Hardness for Attention with Any Temperature](https://mlsanity.com/paper/2505.14840/) (2025)
- [Representing Rule-based Chatbots with Transformers](https://mlsanity.com/paper/2407.10949/) (2024)

## Abstract (arXiv)

Recent works attribute the capability of in-context learning (ICL) in large pre-trained language models to implicitly simulating and fine-tuning an internal model (e.g., linear or 2-layer MLP) during inference. However, such constructions require large memory overhead, which makes simulation of more sophisticated internal models intractable. In this work, we propose an efficient construction, Transformer in Transformer (in short, TinT), that allows a transformer to simulate and fine-tune complex models internally during inference (e.g., pre-trained language models). In particular, we introduce innovative approximation techniques that allow a TinT model with less than 2 billion parameters to simulate and fine-tune a 125 million parameter transformer model within a single forward pass. TinT accommodates many common transformer variants and its design ideas also improve the efficiency of past instantiations of simple models inside transformers. We conduct end-to-end experiments to validate the internal fine-tuning procedure of TinT on various language modeling and downstream tasks. For example, even with a limited one-step budget, we observe TinT for a OPT-125M model improves performance by 4-16% absolute on average compared to OPT-125M. These findings suggest that large pre-trained language models are capable of performing intricate subroutines. To facilitate further work, a modular and extensible codebase for TinT is included.