LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts

• URL: http://arxiv.org/abs/2512.14706v1
• Date: Sun, 07 Dec 2025 10:47:28 GMT
• Title: LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts
• Authors: Krunal Jesani, Dmitry Ignatov, Radu Timofte,
• Abstract summary: We present NN-Caption, an LLM-guided neural architecture search pipeline.<n>It generates runnable image-captioning models by composing CNN encoders from LEMUR's classification backbones.<n>This work presents a pipeline that integrates prompt-based code generation with automatic evaluation.
• Score: 48.83701310501069
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural architecture search (NAS) traditionally requires significant human expertise or automated trial-and-error to design deep learning models. We present NN-Caption, an LLM-guided neural architecture search pipeline that generates runnable image-captioning models by composing CNN encoders from LEMUR's classification backbones with sequence decoders (LSTM/GRU/Transformer) under a strict Net API. Using DeepSeek-R1-0528-Qwen3-8B as the primary generator, we present the prompt template and examples of generated architectures. We evaluate on MS COCO with BLEU-4. The LLM generated dozens of captioning models, with over half successfully trained and producing meaningful captions. We analyse the outcomes of using different numbers of input model snippets (5 vs. 10) in the prompt, finding a slight drop in success rate when providing more candidate components. We also report training dynamics (caption accuracy vs. epochs) and the highest BLEU-4 attained. Our results highlight the promise of LLM-guided NAS: the LLM not only proposes architectures but also suggests hyperparameters and training practices. We identify the challenges encountered (e.g., code hallucinations or API compliance issues) and detail how prompt rules and iterative code fixes addressed them. This work presents a pipeline that integrates prompt-based code generation with automatic evaluation, and adds dozens of novel captioning models to the open LEMUR dataset to facilitate reproducible benchmarking and downstream AutoML research.

Related papers

• Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models [48.83701310501069]
  Large Language Models (LLMs) offer a transformative approach to Neural Architecture Search (NAS)<n>We formulate the search as a sequence of conditional code generation tasks, where an LLM refines architectural specifications based on performance telemetry.<n>We generate a vast corpus of valid, shape-consistent architectures via Abstract Syntax Tree (AST) mutations.<n> Experimental results on CIFAR-100 validate the efficacy of this approach, demonstrating that the model yields statistically significant improvements in accuracy.
  arXiv  Detail & Related papers  (2026-01-13T13:00:30Z)
• Applying RLAIF for Code Generation with API-usage in Lightweight LLMs [15.366324461797582]
  Reinforcement Learning from AI Feedback (RLAIF) has demonstrated significant potential across various domains. This paper introduces an RLAIF framework for improving the code generation abilities of lightweight (1B parameters) LLMs.
  arXiv  Detail & Related papers  (2024-06-28T17:16:03Z)
• CodecLM: Aligning Language Models with Tailored Synthetic Data [51.59223474427153]
  We introduce CodecLM, a framework for adaptively generating high-quality synthetic data for instruction-following abilities. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples.
  arXiv  Detail & Related papers  (2024-04-08T21:15:36Z)
• ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph [142.42275983201978]
  We propose a subgraph-aware self-attention mechanism to imitate the GNN for performing structured reasoning. We also adopt an adaptation tuning strategy to adapt the model parameters with 20,000 subgraphs with synthesized questions. Experiments show that ReasoningLM surpasses state-of-the-art models by a large margin, even with fewer updated parameters and less training data.
  arXiv  Detail & Related papers  (2023-12-30T07:18:54Z)
• Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition [23.172469312225694]
  We propose to utilize an instruction-tuned large language model (LLM) for guiding the text generation process in automatic speech recognition (ASR)<n>The proposed model is built on the joint CTC and attention architecture, with the LLM serving as a front-end feature extractor for the decoder.<n> Experimental results show that the proposed LLM-guided model achieves a relative gain of approximately 13% in word error rates across major benchmarks.
  arXiv  Detail & Related papers  (2023-09-19T11:10:50Z)
• CodeGen2: Lessons for Training LLMs on Programming and Natural Languages [116.74407069443895]
  We unify encoder and decoder-based models into a single prefix-LM. For learning methods, we explore the claim of a "free lunch" hypothesis. For data distributions, the effect of a mixture distribution and multi-epoch training of programming and natural languages on model performance is explored.
  arXiv  Detail & Related papers  (2023-05-03T17:55:25Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)
• Style Attuned Pre-training and Parameter Efficient Fine-tuning for Spoken Language Understanding [19.105304214638075]
  We introduce a novel framework for learning spoken language understanding. The framework consists of a conversational language modeling (CLM) pre-training task and a light encoder architecture. With the framework, we match the performance of state-of-the-art SLU results on Alexa internal datasets and on two public ones, adding only 4.4% parameters per task.
  arXiv  Detail & Related papers  (2020-10-09T03:53:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.