Selective Self-Rehearsal: A Fine-Tuning Approach to Improve Generalization in Large Language Models

• URL: http://arxiv.org/abs/2409.04787v1
• Date: Sat, 7 Sep 2024 10:21:03 GMT
• Title: Selective Self-Rehearsal: A Fine-Tuning Approach to Improve Generalization in Large Language Models
• Authors: Sonam Gupta, Yatin Nandwani, Asaf Yehudai, Mayank Mishra, Gaurav Pandey, Dinesh Raghu, Sachindra Joshi,
• Abstract summary: This paper introduces Selective Self-Rehearsal (SSR), a fine-tuning approach that achieves performance comparable to the standard supervised fine-tuning (SFT) By utilizing the model's correct responses, SSR reduces model specialization during the fine-tuning stage. The effectiveness of SSR is demonstrated through experiments on the task of identifying unanswerable queries across various datasets.
• Score: 19.752712857873043
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task or the characteristics of the training data, resulting in a loss of generalization. This paper introduces Selective Self-Rehearsal (SSR), a fine-tuning approach that achieves performance comparable to the standard supervised fine-tuning (SFT) while improving generalization. SSR leverages the fact that there can be multiple valid responses to a query. By utilizing the model's correct responses, SSR reduces model specialization during the fine-tuning stage. SSR first identifies the correct model responses from the training set by deploying an appropriate LLM as a judge. Then, it fine-tunes the model using the correct model responses and the gold response for the remaining samples. The effectiveness of SSR is demonstrated through experiments on the task of identifying unanswerable queries across various datasets. The results show that standard SFT can lead to an average performance drop of up to $16.7\%$ on multiple benchmarks, such as MMLU and TruthfulQA. In contrast, SSR results in close to $2\%$ drop on average, indicating better generalization capabilities compared to standard SFT.

Related papers

• Fine-Tuning or Fine-Failing? Debunking Performance Myths in Large Language Models [0.8399688944263842]
  Large Language Models (LLMs) have the capability to understand and generate human-like text from input queries. This study extends this concept to the integration of LLMs within Retrieval-Augmented Generation (RAG) pipelines. We evaluate the impact of fine-tuning on the LLMs' capacity for data extraction and contextual understanding.
  arXiv  Detail & Related papers  (2024-06-17T04:35:17Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization [30.61075178799518]
  A test-time adaptation (TTA) method has recently been proposed to adapt the pre-trained ASR model on unlabeled test instances without source data. We propose a novel TTA framework, dubbed SGEM, for general ASR models. SGEM achieves state-of-the-art performance for three mainstream ASR models under various domain shifts.
  arXiv  Detail & Related papers  (2023-06-03T02:27:08Z)
• Adaptive Fine-Grained Predicates Learning for Scene Graph Generation [122.4588401267544]
  General Scene Graph Generation (SGG) models tend to predict head predicates and re-balancing strategies prefer tail categories. We propose an Adaptive Fine-Grained Predicates Learning (FGPL-A) which aims at differentiating hard-to-distinguish predicates for SGG. Our proposed model-agnostic strategy significantly boosts performance of benchmark models on VG-SGG and GQA-SGG datasets by up to 175% and 76% on Mean Recall@100, achieving new state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-07-11T03:37:57Z)
• Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition [65.84978547406753]
  Test-time Adaptation aims to adapt the model trained on source domains to yield better predictions for test samples. Single-Utterance Test-time Adaptation (SUTA) is the first TTA study in speech area to our best knowledge.
  arXiv  Detail & Related papers  (2022-03-27T06:38:39Z)
• Representative Subset Selection for Efficient Fine-Tuning in Self-Supervised Speech Recognition [6.450618373898492]
  We consider the task of identifying an optimal subset of data for efficient fine-tuning in self-supervised speech models for ASR. We present the COWERAGE algorithm for representative subset selection in self-supervised ASR.
  arXiv  Detail & Related papers  (2022-03-18T10:12:24Z)
• Fine-tuning of Pre-trained End-to-end Speech Recognition with Generative Adversarial Networks [10.723935272906461]
  Adversarial training of end-to-end (E2E) ASR systems using generative adversarial networks (GAN) has recently been explored. We introduce a novel framework for fine-tuning a pre-trained ASR model using the GAN objective. Our proposed approach outperforms baselines and conventional GAN-based adversarial models.
  arXiv  Detail & Related papers  (2021-03-10T17:40:48Z)
• One for More: Selecting Generalizable Samples for Generalizable ReID Model [92.40951770273972]
  This paper proposes a one-for-more training objective that takes the generalization ability of selected samples as a loss function. Our proposed one-for-more based sampler can be seamlessly integrated into the ReID training framework.
  arXiv  Detail & Related papers  (2020-12-10T06:37:09Z)
• Joint Contextual Modeling for ASR Correction and Language Understanding [60.230013453699975]
  We propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with language understanding (LU) We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.
  arXiv  Detail & Related papers  (2020-01-28T22:09:25Z)

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.