# JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vector Manipulation

arXiv: https://arxiv.org/abs/2502.20684 · HTML: https://mlsanity.com/paper/2502.20684/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 26 of 26)

- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Causal Machine Learning: A Survey and Open Problems](https://mlsanity.com/paper/2206.15475/) (2022)
- [A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models](https://mlsanity.com/paper/2210.12023/) (2022)
- [Mix and Match: Learning-free Controllable Text Generation using Energy Language Models](https://mlsanity.com/paper/2203.13299/) (2022)
- [Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States](https://mlsanity.com/paper/2402.09733/) (2024)
- [Controlled Text Generation via Language Model Arithmetic](https://mlsanity.com/paper/2311.14479/) (2023)
- [A Latent Space Theory for Emergent Abilities in Large Language Models](https://mlsanity.com/paper/2304.09960/) (2023)
- [Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization](https://mlsanity.com/paper/2210.04492/) (2022)
- [PREADD: Prefix-Adaptive Decoding for Controlled Text Generation](https://mlsanity.com/paper/2307.03214/) (2023)
- [Causality Learning: A New Perspective for Interpretable Machine Learning](https://mlsanity.com/paper/2006.16789/) (2020)
- [Personalized Text Generation with Fine-Grained Linguistic Control](https://mlsanity.com/paper/2402.04914/) (2024)
- [Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs](https://mlsanity.com/paper/2402.11218/) (2024)
- [Reinforcement Learning with Token-level Feedback for Controllable Text Generation](https://mlsanity.com/paper/2403.11558/) (2024)
- [Ensemble Models for Neural Source Code Summarization of Subroutines](https://mlsanity.com/paper/2107.11423/) (2021)
- [Classifiers are Better Experts for Controllable Text Generation](https://mlsanity.com/paper/2205.07276/) (2022)
- [FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation](https://mlsanity.com/paper/2406.09688/) (2024)
- [States Hidden in Hidden States: Implicit Discrete State Representations Emerge in LLMs' Hidden States](https://mlsanity.com/paper/2407.11421/) (2024)

## Built on by (most cited first, 5 of 5)

- [A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data](https://mlsanity.com/paper/2601.17717/) (2026)
- [Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization](https://mlsanity.com/paper/2511.19131/) (2025)
- [Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models](https://mlsanity.com/paper/2601.09260/) (2026)
- [OLLM: Options-based Large Language Models](https://mlsanity.com/paper/2604.19087/) (2026)
- [CAPO: Constraint-Aware Prompt Optimization for LLM Agents](https://mlsanity.com/paper/2608.16068/) (2026)

## Abstract (arXiv)

While large language models (LLMs) have made significant strides in generating coherent and contextually relevant text, they often function as opaque black boxes, trained on vast unlabeled datasets with statistical objectives, lacking an interpretable framework for responsible control. In this paper, we introduce JAM (Just A Move), a novel framework that interprets and controls text generation by integrating cause-effect analysis within the latent space of LLMs. Based on our observations, we uncover the inherent causality in LLM generation, which is critical for producing responsible and realistic outputs. Moreover, we explore latent vectors as fundamental components in LLM architectures, aiming to understand and manipulate them for more effective and efficient controllable text generation. We evaluate our framework using a range of tools, including the HHH criteria, toxicity reduction benchmarks, and GPT-4 alignment measures. Our results show that JAM achieves up to a 22% improvement over previous Controllable Text Generation (CTG) methods across multiple quantitative metrics and human-centric evaluations. Furthermore, JAM demonstrates greater computational efficiency compared to other CTG methods. These results highlight the effectiveness and efficiency of JAM for responsible and realistic text generation, paving the way for more interpretable and controllable models.