Exploring How LLMs Capture and Represent Domain-Specific Knowledge

• URL: http://arxiv.org/abs/2504.16871v2
• Date: Thu, 24 Apr 2025 15:21:54 GMT
• Title: Exploring How LLMs Capture and Represent Domain-Specific Knowledge
• Authors: Mirian Hipolito Garcia, Camille Couturier, Daniel Madrigal Diaz, Ankur Mallick, Anastasios Kyrillidis, Robert Sim, Victor Ruhle, Saravan Rajmohan,
• Abstract summary: We study whether Large Language Models (LLMs) inherently capture domain-specific nuances in natural language.<n>Our experiments probe the domain sensitivity of LLMs by examining their ability to distinguish queries from different domains.<n>We reveal latent domain-related trajectories that indicate the model's internal recognition of query domains.
• Score: 16.84031546207366
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study whether Large Language Models (LLMs) inherently capture domain-specific nuances in natural language. Our experiments probe the domain sensitivity of LLMs by examining their ability to distinguish queries from different domains using hidden states generated during the prefill phase. We reveal latent domain-related trajectories that indicate the model's internal recognition of query domains. We also study the robustness of these domain representations to variations in prompt styles and sources. Our approach leverages these representations for model selection, mapping the LLM that best matches the domain trace of the input query (i.e., the model with the highest performance on similar traces). Our findings show that LLMs can differentiate queries for related domains, and that the fine-tuned model is not always the most accurate. Unlike previous work, our interpretations apply to both closed and open-ended generative tasks

Related papers

• What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization [10.079844840768054]
  Domain Generalization aims to develop models that can generalize to novel and unseen data distributions. We study how model architectures and pre-training objectives impact feature richness. Our framework improves generalization to unseen domains by a maximum test accuracy improvement of over 4%.
  arXiv  Detail & Related papers  (2025-03-09T17:29:01Z)
• Leveraging Domain Knowledge at Inference Time for LLM Translation: Retrieval versus Generation [36.41708236431343]
  Large language models (LLMs) have been increasingly adopted for machine translation (MT)<n>Our work studies domain-adapted MT with LLMs through a careful prompting setup.<n>We find that demonstrations consistently outperform terminology, and retrieval consistently outperforms generation.
  arXiv  Detail & Related papers  (2025-03-06T22:23:07Z)
• Exploring Language Model Generalization in Low-Resource Extractive QA [57.14068405860034]
  We investigate Extractive Question Answering (EQA) with Large Language Models (LLMs) under domain drift.<n>We devise a series of experiments to explain the performance gap empirically.
  arXiv  Detail & Related papers  (2024-09-27T05:06:43Z)
• Boosting Large Language Models with Continual Learning for Aspect-based Sentiment Analysis [33.86086075084374]
  Aspect-based sentiment analysis (ABSA) is an important subtask of sentiment analysis. We propose a Large Language Model-based Continual Learning (textttLLM-CL) model for ABSA.
  arXiv  Detail & Related papers  (2024-05-09T02:00:07Z)
• DIGIC: Domain Generalizable Imitation Learning by Causal Discovery [69.13526582209165]
  Causality has been combined with machine learning to produce robust representations for domain generalization. We make a different attempt by leveraging the demonstration data distribution to discover causal features for a domain generalizable policy. We design a novel framework, called DIGIC, to identify the causal features by finding the direct cause of the expert action from the demonstration data distribution.
  arXiv  Detail & Related papers  (2024-02-29T07:09:01Z)
• Adapt in Contexts: Retrieval-Augmented Domain Adaptation via In-Context Learning [48.22913073217633]
  Large language models (LLMs) have showcased their capability with few-shot inference known as in-context learning. In this paper, we study the UDA problem under an in-context learning setting to adapt language models from the source domain to the target domain without any target labels. We devise different prompting and training strategies, accounting for different LM architectures to learn the target distribution via language modeling.
  arXiv  Detail & Related papers  (2023-11-20T06:06:20Z)
• One Model for All: Large Language Models are Domain-Agnostic Recommendation Systems [43.79001185418127]
  This paper introduces a framework that utilizes pre-trained large language models (LLMs) for domain-agnostic recommendation.<n>Specifically, we mix user's behaviors from multiple domains and item titles into a sentence, then use LLMs for generating user and item representations.
  arXiv  Detail & Related papers  (2023-10-22T13:56:14Z)
• Domain-Controlled Prompt Learning [49.45309818782329]
  Existing prompt learning methods often lack domain-awareness or domain-transfer mechanisms. We propose a textbfDomain-Controlled Prompt Learning for the specific domains. Our method achieves state-of-the-art performance in specific domain image recognition datasets.
  arXiv  Detail & Related papers  (2023-09-30T02:59:49Z)
• Improving Domain Generalization with Domain Relations [77.63345406973097]
  This paper focuses on domain shifts, which occur when the model is applied to new domains that are different from the ones it was trained on. We propose a new approach called D$3$G to learn domain-specific models. Our results show that D$3$G consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-02-06T08:11:16Z)
• Batch Normalization Embeddings for Deep Domain Generalization [50.51405390150066]
  Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. We show a significant increase in classification accuracy over current state-of-the-art techniques on popular domain generalization benchmarks.
  arXiv  Detail & Related papers  (2020-11-25T12:02:57Z)

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.