Replay to Remember: Retaining Domain Knowledge in Streaming Language Models

• URL: http://arxiv.org/abs/2504.17780v1
• Date: Thu, 24 Apr 2025 17:56:22 GMT
• Title: Replay to Remember: Retaining Domain Knowledge in Streaming Language Models
• Authors: Sneh Pillai,
• Abstract summary: Continual learning in large language models (LLMs) typically encounters the critical challenge of catastrophic forgetting.<n>We demonstrate a method combining LoRA and a minimal replay mechanism in a realistic streaming setting.<n>Our experiments reveal that while catastrophic forgetting naturally occurs, even minimal replay significantly stabilizes and partially restores domain-specific knowledge.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual learning in large language models (LLMs) typically encounters the critical challenge of catastrophic forgetting, where previously acquired knowledge deteriorates upon exposure to new data. While techniques like replay buffers and parameter-efficient tuning (e.g., Low-Rank Adaptation or LoRA) have been proposed, few studies investigate real-time domain adaptation under strict computational and data-stream constraints. In this paper, we demonstrate a lightweight method combining LoRA and a minimal replay mechanism in a realistic streaming setting across three diverse knowledge domains: medical question answering, genetics, and law. Using perplexity, semantic similarity, and GPT-based human-like evaluation metrics, we quantify the model's adaptation, forgetting, and recovery over time. Our experiments reveal that while catastrophic forgetting naturally occurs, even minimal replay significantly stabilizes and partially restores domain-specific knowledge. This study contributes practical insights for deploying adaptable LLMs in resource-constrained, real-world scenarios.

Related papers

• How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? [55.33467849079774]
  Low-rank adaptation (LoRA) is a popular and efficient training technique for updating or domain-specific adaptation of Large Language Models.<n>We investigate how new facts can be incorporated into the LLM using LoRA without compromising the previously learned knowledge.
  arXiv  Detail & Related papers  (2025-02-20T12:31:03Z)
• Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve? [19.34040322172224]
  We show that training a model on a text domain could degrade its perplexity on the test portion of the same domain. Our findings will guide us in determining when to adapt a model vs when to rely on its foundational capabilities.
  arXiv  Detail & Related papers  (2024-10-08T00:37:16Z)
• Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training [39.21885486667879]
  Large Language Models (LLMs) exhibit substantial capabilities yet encounter challenges, including hallucination, outdated knowledge, and untraceable reasoning processes. Retrieval-augmented generation (RAG) has emerged as a promising solution, integrating knowledge from external databases to mitigate these challenges. We propose a novel RAG approach known as Retrieval-augmented Adaptive Adrial Training (RAAT)
  arXiv  Detail & Related papers  (2024-05-31T16:24:53Z)
• Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning [9.38259062204602]
  Large language models (LLMs) exhibit remarkable performance in language understanding and generation. LLMs are continuously fine-tuned on complex and diverse domain-specific downstream tasks. A trade-off needs to be kept between learning plasticity and memory stability.
  arXiv  Detail & Related papers  (2024-02-29T05:27:45Z)
• A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia [57.31074448586854]
  Large language models (LLMs) have an impressive ability to draw on novel information supplied in their context. Yet the mechanisms underlying this contextual grounding remain unknown. We present a novel method to study grounding abilities using Fakepedia.
  arXiv  Detail & Related papers  (2023-12-04T17:35:42Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Endogenous Macrodynamics in Algorithmic Recourse [52.87956177581998]
  Existing work on Counterfactual Explanations (CE) and Algorithmic Recourse (AR) has largely focused on single individuals in a static environment. We show that many of the existing methodologies can be collectively described by a generalized framework. We then argue that the existing framework does not account for a hidden external cost of recourse, that only reveals itself when studying the endogenous dynamics of recourse at the group level.
  arXiv  Detail & Related papers  (2023-08-16T07:36:58Z)
• To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis [50.31589712761807]
  Large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its scaling limit for LLMs. We investigate the consequences of repeating pre-training data, revealing that the model is susceptible to overfitting. Second, we examine the key factors contributing to multi-epoch degradation, finding that significant factors include dataset size, model parameters, and training objectives.
  arXiv  Detail & Related papers  (2023-05-22T17:02:15Z)
• Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning [20.92599229976769]
  We show that a simple variation of the first-in-first-out replay buffer is able to overcome the limitation of a replay buffer. We demonstrate this by applying our replay-buffer variation to a deep version of the classical Dyna method.
  arXiv  Detail & Related papers  (2023-03-15T15:21:26Z)
• Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay [67.50637511633212]
  A lifelong learning agent is able to continually learn from potentially infinite streams of pattern sensory data. One major historic difficulty in building agents that adapt is that neural systems struggle to retain previously-acquired knowledge when learning from new samples. This problem is known as catastrophic forgetting (interference) and remains an unsolved problem in the domain of machine learning to this day.
  arXiv  Detail & Related papers  (2021-12-09T07:11:14Z)
• Studying Catastrophic Forgetting in Neural Ranking Models [3.8596788671326947]
  We study in what extent neural ranking models catastrophically forget old knowledge acquired from previously observed domains after acquiring new knowledge. Our experiments show that the effectiveness of neuralIR ranking models is achieved at the cost of catastrophic forgetting. We believe that the obtained results can be useful for both theoretical and practical future work in neural IR.
  arXiv  Detail & Related papers  (2021-01-18T10:42:57Z)

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.