SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations

• URL: http://arxiv.org/abs/2305.13235v2
• Date: Tue, 23 May 2023 09:26:37 GMT
• Title: SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations
• Authors: Jesus Solano, Oana-Maria Camburu, Pasquale Minervini
• Abstract summary: We propose SparseFit, a sparse few-shot fine-tuning strategy that leverages discrete prompts to jointly generate predictions and NLEs. We perform automatic and human evaluations to assess the quality of the model-generated NLEs, finding that fine-tuning only 6.8% of the model parameters leads to competitive results.
• Score: 22.280037513501338
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Explaining the decisions of neural models is crucial for ensuring their trustworthiness at deployment time. Using Natural Language Explanations (NLEs) to justify a model's predictions has recently gained increasing interest. However, this approach usually demands large datasets of human-written NLEs for the ground-truth answers, which are expensive and potentially infeasible for some applications. For models to generate high-quality NLEs when only a few NLEs are available, the fine-tuning of Pre-trained Language Models (PLMs) in conjunction with prompt-based learning recently emerged. However, PLMs typically have billions of parameters, making fine-tuning expensive. We propose SparseFit, a sparse few-shot fine-tuning strategy that leverages discrete prompts to jointly generate predictions and NLEs. We experiment with SparseFit on the T5 model and four datasets and compare it against state-of-the-art parameter-efficient fine-tuning techniques. We perform automatic and human evaluations to assess the quality of the model-generated NLEs, finding that fine-tuning only 6.8% of the model parameters leads to competitive results for both the task performance and the quality of the NLEs.

Related papers

• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [90.4820014819937]
  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 finetuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, SELM significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• Advancing the Robustness of Large Language Models through Self-Denoised Smoothing [50.54276872204319]
  Large language models (LLMs) have achieved significant success, but their vulnerability to adversarial perturbations has raised considerable concerns. We propose to leverage the multitasking nature of LLMs to first denoise the noisy inputs and then to make predictions based on these denoised versions. Unlike previous denoised smoothing techniques in computer vision, which require training a separate model to enhance the robustness of LLMs, our method offers significantly better efficiency and flexibility.
  arXiv  Detail & Related papers  (2024-04-18T15:47:00Z)
• A synthetic data approach for domain generalization of NLI models [13.840374911669167]
  Natural Language Inference (NLI) remains an important benchmark task for LLMs. We show that synthetic high-quality datasets can adapt NLI models for zero-shot use in downstream applications. We show that models trained on this data have the best generalization to completely new downstream test settings.
  arXiv  Detail & Related papers  (2024-02-19T18:55:16Z)
• Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding [38.11411155621616]
  We study self-training as one of the predominant semi-supervised learning approaches. We present UPET, a novel Uncertainty-aware self-Training framework. We show that UPET achieves a substantial improvement in terms of performance and efficiency.
  arXiv  Detail & Related papers  (2023-10-19T02:18:29Z)
• Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost [6.662800021628275]
  We study the use of large language models (LLMs) for annotating inputs and improving the generalization of NLP models. We propose a sampling strategy based on the difference in prediction scores between the base model and the finetuned NLP model.
  arXiv  Detail & Related papers  (2023-06-27T19:29:55Z)
• KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations [52.33256203018764]
  We leverage external knowledge bases to significantly improve on an existing adversarial attack for detecting inconsistent NLEs. We show that models with higher NLE quality do not necessarily generate fewer inconsistencies.
  arXiv  Detail & Related papers  (2023-06-05T15:51:58Z)
• ZeroGen$^+$: Self-Guided High-Quality Data Generation in Efficient Zero-Shot Learning [97.2907428983142]
  ZeroGen attempts to purely use PLM to generate data and train a tiny model without relying on task-specific annotation. We propose a noise-robust bi-level re-weighting framework which is able to learn the per-sample weights measuring the data quality without requiring any gold data.
  arXiv  Detail & Related papers  (2022-05-25T11:38:48Z)
• Efficient Nearest Neighbor Language Models [114.40866461741795]
  Non-parametric neural language models (NLMs) learn predictive distributions of text utilizing an external datastore. We show how to achieve up to a 6x speed-up in inference speed while retaining comparable performance.
  arXiv  Detail & Related papers  (2021-09-09T12:32:28Z)
• e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks [52.918087305406296]
  We introduce e-ViL, a benchmark for evaluate explainable vision-language tasks. We also introduce e-SNLI-VE, the largest existing dataset with NLEs. We propose a new model that combines UNITER, which learns joint embeddings of images and text, and GPT-2, a pre-trained language model.
  arXiv  Detail & Related papers  (2021-05-08T18:46:33Z)
• Automated essay scoring using efficient transformer-based language models [0.5161531917413708]
  Automated Essay Scoring (AES) is a cross-disciplinary effort involving Education, Linguistics, and Natural Language Processing (NLP) Large pretrained transformer-based language models have dominated the current state-of-the-art in many NLP tasks. This paper is to challenge the paradigm in NLP that bigger is better when it comes to AES.
  arXiv  Detail & Related papers  (2021-02-25T19:28:39Z)

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.