Prompt-Efficient Fine-Tuning for GPT-like Deep Models to Reduce Hallucination and to Improve Reproducibility in Scientific Text Generation Using Stochastic Optimisation Techniques

• URL: http://arxiv.org/abs/2411.06445v1
• Date: Sun, 10 Nov 2024 12:28:09 GMT
• Title: Prompt-Efficient Fine-Tuning for GPT-like Deep Models to Reduce Hallucination and to Improve Reproducibility in Scientific Text Generation Using Stochastic Optimisation Techniques
• Authors: Daniil Sulimov,
• Abstract summary: Large Language Models (LLMs) are increasingly adopted for complex scientific text generation tasks. They often suffer from limitations in accuracy, consistency, and hallucination control. This thesis introduces a. ‘Fine-Tuning’ approach tailored for GPT-like models, aiming to mitigate hallucinations and enhance adapters.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are increasingly adopted for complex scientific text generation tasks, yet they often suffer from limitations in accuracy, consistency, and hallucination control. This thesis introduces a Parameter-Efficient Fine-Tuning (PEFT) approach tailored for GPT-like models, aiming to mitigate hallucinations and enhance reproducibility, particularly in the computational domain of mass spectrometry. We implemented Low-Rank Adaptation (LoRA) adapters to refine GPT-2, termed MS-GPT, using a specialized corpus of mass spectrometry literature. Through novel evaluation methods applied to LLMs, including BLEU, ROUGE, and Perplexity scores, the fine-tuned MS-GPT model demonstrated superior text coherence and reproducibility compared to the baseline GPT-2, confirmed through statistical analysis with the Wilcoxon rank-sum test. Further, we propose a reproducibility metric based on cosine similarity of model outputs under controlled prompts, showcasing MS-GPT's enhanced stability. This research highlights PEFT's potential to optimize LLMs for scientific contexts, reducing computational costs while improving model reliability.

Related papers

• Supervised Optimism Correction: Be Confident When LLMs Are Sure [91.7459076316849]
  We establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning. We show that the widely used beam search method suffers from unacceptable over-optimism. We propose Supervised Optimism Correction, which introduces a simple yet effective auxiliary loss for token-level $Q$-value estimations.
  arXiv  Detail & Related papers  (2025-04-10T07:50:03Z)
• GPT Meets Graphs and KAN Splines: Testing Novel Frameworks on Multitask Fine-Tuned GPT-2 with LoRA [0.0]
  We explore the potential of integrating learnable and interpretable modules--specifically Kolmogorov-Arnold Networks (KAN) and graph-based representations--within a pre-trained GPT-2 model.
  arXiv  Detail & Related papers  (2025-03-25T19:58:25Z)
• Preference Alignment Improves Language Model-Based TTS [76.70693823683091]
  preference alignment algorithms adjust LMs to align with the preferences of reward models, enhancing the desirability of the generated content. With a 1.15B parameter LM-based TTS model, we demonstrate that preference alignment consistently improves intelligibility, speaker similarity, and proxy subjective evaluation scores.
  arXiv  Detail & Related papers  (2024-09-19T01:58:19Z)
• THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models [0.0]
  Hallucination, the generation of factually incorrect content, is a growing challenge in Large Language Models. This paper introduces THaMES, an integrated framework and library addressing this gap. THaMES offers an end-to-end solution for evaluating and mitigating hallucinations in LLMs.
  arXiv  Detail & Related papers  (2024-09-17T16:55:25Z)
• GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs [51.02233412547456]
  We introduce a novel PEFT method, called Gaussian noise Injected Fine Tuning of Salient Weights (GIFT-SW) Our method updates only salient columns, while injecting Gaussian noise into non-salient ones. Experiments with LLaMA models demonstrate that GIFT-SW outperforms full fine-tuning and modern PEFT methods under the same computational budget.
  arXiv  Detail & Related papers  (2024-08-27T14:41:14Z)
• Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization [17.20276556057748]
  Large Language Models (LLMs) have been found to memorize and recite some of the textual sequences from their training set verbatim. This Textual Sequence Memorization (TSM) phenomenon leads to a high demand to regulate LLM output to prevent it from generating certain memorized text. Existing methods for TSM erasure fail to forget massive memorized samples without substantially jeopardizing the model utility.
  arXiv  Detail & Related papers  (2024-08-09T10:26:11Z)
• GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning [48.71952325015267]
  We apply PEFT methods to a modified Retrieval-Enhanced Transformer (RETRO) and a baseline GPT model across several sizes. We show that RETRO models outperform GPT models in zero-shot settings due to their unique pre-training process. This work presents the first comprehensive comparison of various PEFT methods integrated with RAG, applied to both GPT and RETRO models.
  arXiv  Detail & Related papers  (2024-07-05T14:16:47Z)
• Biomedical knowledge graph-optimized prompt generation for large language models [1.6658478064349376]
  Large Language Models (LLMs) are being adopted at an unprecedented rate, yet still face challenges in knowledge-intensive domains like biomedicine. Here, we introduce a token-optimized and robust Knowledge Graph-based Retrieval Augmented Generation framework.
  arXiv  Detail & Related papers  (2023-11-29T03:07:00Z)
• CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration [59.48235003469116]
  We show that data augmentation consistently enhances OOD performance. We also show that CF augmented models which are easier to calibrate also exhibit much lower entropy when assigning importance.
  arXiv  Detail & Related papers  (2023-09-14T16:16:40Z)
• Physics-based Reduced Order Modeling for Uncertainty Quantification of Guided Wave Propagation using Bayesian Optimization [0.0]
  Guided wave propagation (GWP) is commonly employed for the inspection of structures in structural health monitoring (SHM) Uncertainty quantification (UQ) is regularly applied to improve the reliability of predictions. We propose a machine learning (ML)-based reduced order model (ROM) to decrease the computational time related to the simulation of the GWP.
  arXiv  Detail & Related papers  (2023-07-18T22:03:43Z)
• Efficient GPT Model Pre-training using Tensor Train Matrix Representation [65.96485282393361]
  Large-scale transformer models feature billions of parameters, leading to difficulties in their deployment and prohibitive training costs from scratch. To reduce the number of parameters in the GPT-2 architecture, we replace the matrices of fully-connected layers with the corresponding Train Matrix(TTM) structure. The resulting GPT-based model stores up to 40% fewer parameters, showing the perplexity comparable to the original model.
  arXiv  Detail & Related papers  (2023-06-05T08:38:25Z)
• Spectral Tensor Train Parameterization of Deep Learning Layers [136.4761580842396]
  We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. We show the effects of neural network compression in the classification setting and both compression and improved stability training in the generative adversarial training setting.
  arXiv  Detail & Related papers  (2021-03-07T00:15:44Z)

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.