mlsanityData to 14 Oct 2026

Towards the Readability of LLM-Generated Codes through Multitask Representation Engineering

arXiv 2606.06214 ↗First posted 4 Jun 2026cs.SE cs.AIcited by 0

On the map: Mechanistic interpretability → Knowledge and representations inside LLMs

Abstract (arXiv)

Correctness and readability are key measures of code quality, respectively ensuring functional fidelity and ease of comprehension. While most existing research focuses on improving the correctness of large language models~(LLMs) generated codes, readability remains under-addressed. Enhancing readability through targeted control is challenging due to its subjective nature. In this article, we employ representation engineering~(RepE) as the targeted control method given its characteristics of low data dependency and low computational cost. Prior work on RepE has primarily focused on the targeted control for a single task, but improving the code readability requires the control across multiple tasks. Accordingly we proposes the multitask RepE framework and theoretically discuss the impact of the multitask steering method on the tradeoff between the code readability and correctness. We further provide comprehensive experiments in support. All the relevant implementations are open-source and available upon request.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge and representations inside LLMs, one of 13 directions in Mechanistic interpretability. Builds on 17 of its 32 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

17 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Representation Engineering: A Top-Down Approach to AI Transparency2 Oct

Other references · 16

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2021Program Synthesis with Large Language Modelscited by 3,637
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  4. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  5. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  6. 2024A Survey on Large Language Models for Code Generationcited by 658
  7. 2024ORPO: Monolithic Preference Optimization without Reference Modelcited by 562
  8. 2023RRHF: Rank Responses to Align Language Models with Human Feedback without tearscited by 463
  9. 2018code2vec: Learning Distributed Representations of Codecited by 250
  10. 2023Full Parameter Fine-tuning for Large Language Models with Limited Resourcescited by 134
  11. 2023Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytescited by 55
  12. 2024Extending Activation Steering to Broad Skills and Multiple Behaviourscited by 40
4 more
  1. 2024Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methodscited by 28
  2. 2024BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Modelscited by 27
  3. 2025Correctness Assessment of Code Generated by Large Language Models Using Internal Representationscited by 17
  4. 2025Code Readability in the Age of Large Language Models: An Industrial Case Study from Atlassiancited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation
  2. 2025Human-Aligned Code Readability Assessment with Large Language Models ↗
  3. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
  4. 2025CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models
  5. 2025Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning
  6. 2025Improving LLM-Generated Code Quality with GRPO
  7. 2023Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency
  8. 2025Towards Advancing Code Generation with Large Language Models: A Research Roadmap