# Manipulating Transformer-Based Models: Controllability, Steerability, and Robust Interventions

arXiv: https://arxiv.org/abs/2509.04549 · HTML: https://mlsanity.com/paper/2509.04549/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 17 references that are in the map.
- First posted on arXiv 4 Sep 2025.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Understanding neural networks with reproducing kernel Banach spaces](https://mlsanity.com/paper/2109.09710/) (2021)
- [Prompt Injection Attacks on Large Language Models in Oncology](https://mlsanity.com/paper/2407.18981/) (2024)
- [ALBETO and DistilBETO: Lightweight Spanish Language Models](https://mlsanity.com/paper/2204.09145/) (2022)

## Built on by (most cited first, 2 of 2)

- [Steerability of Instrumental-Convergence Tendencies in LLMs](https://mlsanity.com/paper/2601.01584/) (2026)
- [A Responsive Present, a Shared Past, a Social Other: Teens' Overreliance on Companion AI Chatbots](https://mlsanity.com/paper/2609.14843/) (2026)

## Abstract (arXiv)

Transformer-based language models excel in NLP tasks, but fine-grained control remains challenging. This paper explores methods for manipulating transformer models through principled interventions at three levels: prompts, activations, and weights. We formalize controllable text generation as an optimization problem addressable via prompt engineering, parameter-efficient fine-tuning, model editing, and reinforcement learning. We introduce a unified framework encompassing prompt-level steering, activation interventions, and weight-space edits. We analyze robustness and safety implications, including adversarial attacks and alignment mitigations. Theoretically, we show minimal weight updates can achieve targeted behavior changes with limited side-effects. Empirically, we demonstrate >90% success in sentiment control and factual edits while preserving base performance, though generalization-specificity trade-offs exist. We discuss ethical dual-use risks and the need for rigorous evaluation. This work lays groundwork for designing controllable and robust language models.