Understanding the Effects of Domain Finetuning on LLMs

• URL: http://arxiv.org/abs/2510.09359v1
• Date: Fri, 10 Oct 2025 13:14:06 GMT
• Title: Understanding the Effects of Domain Finetuning on LLMs
• Authors: Eshaan Tanwar, Deepak Nathani, William Yang Wang, Tanmoy Chakraborty,
• Abstract summary: We present the first systematic study of domain-specific fine-tuning in large medical language models.<n>Our analysis reveals that fine-tuning modifies only a small subset of the representational subspace.<n>To interpret these changes in subspaces, we propose tuning vectors, which explicitly capture the directional parameter shifts induced by fine-tuning.
• Score: 60.874016669351874
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) fine-tuned for specific domains exhibit strong performance; however, the underlying mechanisms by which this fine-tuning reshapes their parametric space are not well understood. Prior works primarily focus on auto-regressive or general-purpose instruct models, leaving domain-specialised LLMs under-explored. We present the first systematic study of domain-specific fine-tuning in large medical language models. Our analysis reveals that fine-tuning modifies only a small subset of the representational subspace, essentially preserving the pre-trained model's representation. To interpret these changes in subspaces, we propose tuning vectors, a novel framework inspired by task vectors, which explicitly capture the directional parameter shifts induced by fine-tuning. We demonstrate that these vectors are critical for enhancing both instruction-following and generation quality. Furthermore, combining tuning vectors across different domains yields improved generalisation. Upon closer inspection of directional alignment, we find these vectors primarily write new directional information into the MLP layers of the model, while amplifying existing directions in attention heads. Our findings offer new insights into LLM adaptation and provide a general, interpretable framework for analysing specialisation in large language models.

Related papers

• Reasoning-Driven Multimodal LLM for Domain Generalization [72.00754603114187]
  We study the role of reasoning in domain generalization using DomainBed-Reasoning dataset.<n>We propose RD-MLDG, a framework with two components: MTCT (Multi-Task Cross-Training) and SARR (Self-Aligned Reasoning Regularization)<n>Experiments on standard DomainBed datasets demonstrate that RD-MLDG achieves complementary state-of-the-art performances.
  arXiv  Detail & Related papers  (2026-02-27T08:10:06Z)
• Rank-1 LoRAs Encode Interpretable Reasoning Signals [0.764671395172401]
  Reasoning models leverage inference-time compute to significantly enhance the performance of language models on logical tasks.<n>Despite their wide adoption, the mechanisms underpinning the enhanced performance of these reasoning models are not well understood.<n>We show that the majority of new capabilities in reasoning models can be elicited by small, single-rank changes to base model parameters.
  arXiv  Detail & Related papers  (2025-11-10T06:00:25Z)
• Understanding Post-Training Structural Changes in Large Language Models [3.054513120350576]
  Post-training fundamentally alters the behavior of large language models (LLMs)<n>This work focuses on two widely adopted post-training methods: instruction tuning and long-chain-of-thought (Long-CoT) distillation.
  arXiv  Detail & Related papers  (2025-09-22T15:03:36Z)
• Enhancing Semantic Segmentation with Continual Self-Supervised Pre-training [11.897717409259492]
  Self-supervised learning (SSL) has emerged as a central paradigm for training foundation models.<n>We propose GLARE, a novel continual self-supervised pre-training task designed to enhance downstream segmentation performance.
  arXiv  Detail & Related papers  (2025-09-22T14:11:02Z)
• Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors [12.331740215947677]
  We study lightweight steering vectors inserted into the base model's residual stream and trained with a reinforcement-learning objective.<n>We find that (i) the last-layer steering vector acts like a token-substitution bias concentrated on the first generated token, consistently boosting tokens such as "To" and "Step"<n>We also show that steering vectors (i) transfer to other models, (ii) combine across layers when trained in isolation, and (iii) concentrate magnitude on meaningful prompt segments under adaptive token-wise scaling.
  arXiv  Detail & Related papers  (2025-09-08T12:26:31Z)
• Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models [68.57424628540907]
  Large language models (LLMs) often develop learned mechanisms specialized to specific datasets.<n>We introduce a fine-tuning approach designed to enhance generalization by identifying and pruning neurons associated with dataset-specific mechanisms.<n>Our method employs Integrated Gradients to quantify each neuron's influence on high-confidence predictions, pinpointing those that disproportionately contribute to dataset-specific performance.
  arXiv  Detail & Related papers  (2025-07-12T08:10:10Z)
• Weight Spectra Induced Efficient Model Adaptation [54.8615621415845]
  Fine-tuning large-scale foundation models incurs prohibitive computational costs.<n>We show that fine-tuning predominantly amplifies the top singular values while leaving the remainder largely intact.<n>We propose a novel method that leverages learnable rescaling of top singular directions.
  arXiv  Detail & Related papers  (2025-05-29T05:03:29Z)
• Demystifying Singular Defects in Large Language Models [61.98878352956125]
  In large language models (LLMs), the underlying causes of high-norm tokens remain largely unexplored.<n>We provide both theoretical insights and empirical validation across a range of recent models.<n>We showcase two practical applications of these findings: the improvement of quantization schemes and the design of LLM signatures.
  arXiv  Detail & Related papers  (2025-02-10T20:09:16Z)
• 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)
• Transformer Block Coupling and its Correlation with Generalization in LLMs [3.007031501305338]
  We analyze the trajectories of token embeddings as they pass through transformer blocks, linearizing the system along these trajectories through their Jacobian matrices.<n>We uncover the phenomenon of textbftransformer block coupling in a multitude of Large Language Models, characterized by the coupling of their top singular vectors across tokens and depth.<n>We further investigate how these properties emerge during training, observing a progressive development of coupling, increased linearity, and layer-wise exponential growth in token trajectories.
  arXiv  Detail & Related papers  (2024-07-10T16:30:27Z)
• Unveiling the Generalization Power of Fine-Tuned Large Language Models [81.70754292058258]
  We investigate whether fine-tuning affects the intrinsic generalization ability intrinsic to Large Language Models (LLMs) Our main findings reveal that models fine-tuned on generation and classification tasks exhibit dissimilar behaviors in generalizing to different domains and tasks. We observe that integrating the in-context learning strategy during fine-tuning on generation tasks can enhance the model's generalization ability.
  arXiv  Detail & Related papers  (2024-03-14T08:18:59Z)
• Mitigate Domain Shift by Primary-Auxiliary Objectives Association for Generalizing Person ReID [39.98444065846305]
  ReID models struggle in learning domain-invariant representation solely through training on an instance classification objective. We introduce a method that guides model learning of the primary ReID instance classification objective by a concurrent auxiliary learning objective on weakly labeled pedestrian saliency detection. Our model can be extended with the recent test-time diagram to form the PAOA+, which performs on-the-fly optimization against the auxiliary objective.
  arXiv  Detail & Related papers  (2023-10-24T15:15:57Z)
• Autoregressive Structured Prediction with Language Models [73.11519625765301]
  We describe an approach to model structures as sequences of actions in an autoregressive manner with PLMs. Our approach achieves the new state-of-the-art on all the structured prediction tasks we looked at.
  arXiv  Detail & Related papers  (2022-10-26T13:27:26Z)
• Disentangled Representation Learning and Generation with Manifold Optimization [10.69910379275607]
  This work presents a representation learning framework that explicitly promotes disentanglement by encouraging directions of variations. Our theoretical discussion and various experiments show that the proposed model improves over many VAE variants in terms of both generation quality and disentangled representation learning.
  arXiv  Detail & Related papers  (2020-06-12T10:00:49Z)

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.