LLM attribution analysis across different fine-tuning strategies and model scales for automated code compliance

• URL: http://arxiv.org/abs/2604.15589v1
• Date: Thu, 16 Apr 2026 23:54:26 GMT
• Title: LLM attribution analysis across different fine-tuning strategies and model scales for automated code compliance
• Abstract summary: This paper employs a perturbation-based attribution analysis to compare the interpretive behaviors of large language models (LLMs) across different fine-tuning strategies.<n>Our results show that FFT produces attribution patterns that are statistically different and more focused than those from parameter-efficient fine-tuning methods.
• Score: 1.154460794319478
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing research on large language models (LLMs) for automated code compliance has primarily focused on performance, treating the models as black boxes and overlooking how training decisions affect their interpretive behavior. This paper addresses this gap by employing a perturbation-based attribution analysis to compare the interpretive behaviors of LLMs across different fine-tuning strategies such as full fine-tuning (FFT), low-rank adaptation (LoRA) and quantized LoRA fine-tuning, as well as the impact of model scales which include varying LLM parameter sizes. Our results show that FFT produces attribution patterns that are statistically different and more focused than those from parameter-efficient fine-tuning methods. Furthermore, we found that as model scale increases, LLMs develop specific interpretive strategies such as prioritizing numerical constraints and rule identifiers in the building text, albeit with performance gains in semantic similarity of the generated and reference computer-processable rules plateauing for models larger than 7B. This paper provides crucial insights into the explainability of these models, taking a step toward building more transparent LLMs for critical, regulation-based tasks in the Architecture, Engineering, and Construction industry.

Related papers

• Spectral Signatures of Large Language Models [13.878105276531976]
  We propose spectral shape-based metrics for managing and quantifying large language models (LLMs)<n>Our approach uses the shape information of the weight empirical spectral density as a compact spectral signature of each model.<n>This signature captures intrinsic properties of pretrained models and remains robust during post-training, making it suitable for model-level analysis.
  arXiv  Detail & Related papers  (2026-07-03T14:30:22Z)
• Linear-LLM-SCM: Benchmarking LLMs for Coefficient Elicitation in Linear-Gaussian Causal Models [28.281361951823765]
  We introduce Linear-LLM-SCM, a plug-and-play benchmarking framework for evaluating large language models (LLMs)<n>We show challenges in such benchmarking tasks, namely, strongity in the results in some of the models and susceptibility to DAG misspecification via spurious edges in the continuous domains.<n>We also open-source the benchmarking framework so that researchers can utilize their DAGs and any off-the-shelf LLMs plug-and-play for evaluation in their domains effortlessly.
  arXiv  Detail & Related papers  (2026-02-10T20:49:01Z)
• How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns [51.02752099869218]
  Large Language Models (LLMs) display strikingly different generalization behaviors.<n>We introduce a novel benchmark that decomposes reasoning into atomic core skills.<n>We show that RL-tuned models maintain more stable behavioral profiles and resist collapse in reasoning skills, whereas SFT models exhibit sharper drift and overfit to surface patterns.
  arXiv  Detail & Related papers  (2025-12-30T08:16:20Z)
• Enhancing LLM Robustness to Perturbed Instructions: An Empirical Study [8.827173113748701]
  We study character- and word-level edits of task-specific instructions, which substantially degrade downstream performance.<n>We find that, on average, self-denoising achieves substantially higher performance gains than alternative strategies.
  arXiv  Detail & Related papers  (2025-04-03T16:17:56Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment.<n>We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• Exploring Model Editing for LLM-based Aspect-Based Sentiment Classification [17.512415475301395]
  We investigate model editing to serve an efficient method for adapting large language models (LLMs) to solve aspect-based sentiment classification.<n>Our findings reveal that a distinct set of mid-layer representations is essential for detecting the sentiment polarity of given aspect words.<n>We develop a model editing approach that focuses exclusively on these critical parts of the LLM, leading to a more efficient method for adapting LLMs.
  arXiv  Detail & Related papers  (2025-03-19T11:21:37Z)
• Latent Thought Models with Variational Bayes Inference-Time Computation [52.63299874322121]
  Latent Thought Models (LTMs) incorporate explicit latent thought vectors that follow an explicit prior model in latent space.<n>LTMs demonstrate superior sample and parameter efficiency compared to autoregressive models and discrete diffusion models.
  arXiv  Detail & Related papers  (2025-02-03T17:50:34Z)
• Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning [65.23593936798662]
  We show that fine-tuning with LLM-generated data improves target task performance and reduces non-target task degradation.<n>This is the first work to provide an empirical explanation based on token perplexity reduction to mitigate catastrophic forgetting in LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2025-01-24T08:18:56Z)
• The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities [51.594836904623534]
  We investigate whether instruction-tuned models possess fundamentally different capabilities from base models that are prompted using in-context examples.<n>We show that the performance of instruction-tuned models is significantly correlated with the in-context performance of their base counterparts.<n>Specifically, we extend this understanding to instruction-tuned models, suggesting that their pretraining data similarly sets a limiting boundary on the tasks they can solve.
  arXiv  Detail & Related papers  (2025-01-15T10:57:55Z)
• LLMs are Also Effective Embedding Models: An In-depth Overview [41.34518828980852]
  Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks.<n>Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift from traditional encoder-only models like ELMo and BERT to decoder-only, large-scale LLMs like GPT, LLaMA, and Mistral.
  arXiv  Detail & Related papers  (2024-12-17T06:48:24Z)
• Interpreting token compositionality in LLMs: A robustness analysis [10.777646083061395]
  Constituent-Aware Pooling (CAP) is a methodology designed to analyse how large language models process linguistic structures.<n>CAP intervenes in model activations through constituent-based pooling at various model levels.<n>Our findings highlight fundamental limitations in current transformer architectures regarding compositional semantics processing and model interpretability.
  arXiv  Detail & Related papers  (2024-10-16T18:10:50Z)
• Performance Law of Large Language Models [58.32539851241063]
  Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources. Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources without extensive experiments.
  arXiv  Detail & Related papers  (2024-08-19T11:09:12Z)

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.