mlsanityData to 14 Oct 2026

ChipLingo: A Systematic Training Framework for Large Language Models in EDA

arXiv 2604.27415 ↗First posted 30 Apr 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

With the rapid advancement of semiconductor technology, Electronic Design Automation (EDA) has become an increasingly knowledge-intensive and document-driven engineering domain. Although large language models (LLMs) have shown strong general capabilities, applying them directly to EDA remains challenging due to limited domain expertise, cross-tool knowledge confusion, and degraded retrieval-augmented generation (RAG) performance after domain training. To address these issues, this paper presents ChipLingo, a systematic training pipeline for domain-adapted LLMs tailored to EDA scenarios. ChipLingo consists of three stages: domain corpus construction with multi-source data curation and QA augmentation, domain-adaptive pretraining with comparisons of different parameter training strategies, and instruction alignment with RAG scenario training under diverse retrieval conditions. We also curate an internal benchmark, EDA-Bench, covering representative EDA tool scenarios, with plans for public release. Experiments show that ChipLingo-8B achieves 59.7% accuracy on EDA-Bench, outperforming the same-scale base model and some larger general-purpose models. ChipLingo-32B reaches 70.02%, approaching leading closed-source commercial models. Further analysis shows that QA augmentation improves domain performance, Partial FT offers a better balance between adaptation and general capability retention than LoRA, and explicit RAG scenario training mitigates the decline in retrieval utilization after domain training. These results demonstrate the practical value of systematic domain training for knowledge-intensive EDA tasks and provide a foundation for future EDA agents and external-knowledge-driven systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 30 references that are in the map. First posted on arXiv 30 Apr 2026.

Builds on

25 of 30 references.

References · 25

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  7. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  8. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  9. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  10. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  11. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  12. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
13 more
  1. 2024Measuring short-form factuality in large language modelscited by 373
  2. 2023AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuningcited by 357
  3. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 262
  4. 2023VerilogEval: Evaluating Large Language Models for Verilog Code Generationcited by 252
  5. 2023ChipNeMo: Domain-Adapted LLMs for Chip Designcited by 174
  6. 2024SaulLM-7B: A pioneering Large Language Model for Lawcited by 142
  7. 2023ChatEDA: A Large Language Model Powered Autonomous Agent for EDAcited by 122
  8. 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extractioncited by 93
  9. 2024Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledgecited by 50
  10. 2024Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QAcited by 28
  11. 2025How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?cited by 13
  12. 2024ChipExpert: The Open-Source Integrated-Circuit-Design-Specific Large Language Modelcited by 2
  13. 2026iScript: A Domain-Adapted Large Language Model and Benchmark for Physical Design Tcl Script Generationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Large Language Models (LLMs) for Electronic Design Automation (EDA)
  2. 2025Improving LLM-Powered EDA Assistants with RAFT
  3. 2025JARVIS: A Multi-Agent Code Assistant for High-Quality EDA Script Generation
  4. 2025AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents
  5. 2024Ask-EDA: A Design Assistant Empowered by LLM, Hybrid RAG and Abbreviation De-hallucination
  6. 2025MMCircuitEval: A Comprehensive Multimodal Circuit-Focused Benchmark for Evaluating LLMs
  7. 2024Can Low-Rank Knowledge Distillation in LLMs be Useful for Microelectronic Reasoning?
  8. 2026From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA