AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy

• URL: http://arxiv.org/abs/2409.19750v1
• Date: Sun, 29 Sep 2024 16:02:22 GMT
• Title: AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy
• Authors: Rui Pan, Tuan Dung Nguyen, Hardik Arora, Alberto Accomazzi, Tirthankar Ghosal, Yuan-Sen Ting,
• Abstract summary: This study aims to quantitatively assess specialized LLMs in astronomy. We find that the previously released AstroLLaMA series, based on LLaMA-2-7B, underperforms compared to the base model. Despite the observed catastrophic forgetting in smaller models, our results indicate that continual pretraining on the 70B model can yield significant improvements.
• Score: 4.729846733874557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual pretraining of large language models on domain-specific data has been proposed to enhance performance on downstream tasks. In astronomy, the previous absence of astronomy-focused benchmarks has hindered objective evaluation of these specialized LLM models. Leveraging a recent initiative to curate high-quality astronomical MCQs, this study aims to quantitatively assess specialized LLMs in astronomy. We find that the previously released AstroLLaMA series, based on LLaMA-2-7B, underperforms compared to the base model. We demonstrate that this performance degradation can be partially mitigated by utilizing high-quality data for continual pretraining, such as summarized text from arXiv. Despite the observed catastrophic forgetting in smaller models, our results indicate that continual pretraining on the 70B model can yield significant improvements. However, the current supervised fine-tuning dataset still constrains the performance of instruct models. In conjunction with this study, we introduce a new set of models, AstroLLaMA-3-8B and AstroLLaMA-2-70B, building upon the previous AstroLLaMA series.

Related papers

• Training Language Models to Critique With Multi-agent Feedback [102.42751835338233]
  MultiCritique pipeline improves critique ability of LLMs by utilizing multi-agent feedback. pipeline aggregates high-quality critiques from multiple agents instead of a single model. Our fine-tuned 7B model significantly surpasses other advanced 7B-13B open-source models.
  arXiv  Detail & Related papers  (2024-10-20T04:57:45Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• AstroMLab 1: Who Wins Astronomy Jeopardy!? [4.162245706139047]
  This dataset comprises 4,425 multiple-choice questions curated from the Annual Review of Astronomy and Astrophysics. Claude-3.5-Sonnet outperforms competitors by up to 4.6 percentage points, achieving 85.0% accuracy. Open-source models have rapidly improved, with LLaMA-3-70b (80.6%) and Qwen-2-72b (77.7%) now competing with some of the best proprietary models.
  arXiv  Detail & Related papers  (2024-07-15T19:28:14Z)
• Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On [55.449818944278526]
  We introduce the Skywork-Math model series, supervised fine-tuned (SFT) on common 7B language models. Skywork-Math 7B has achieved impressive accuracies of 51.2% on the competition-level MATH benchmark. We provide several practical takeaways to enhance math reasoning abilities in LLMs for both research and industry applications.
  arXiv  Detail & Related papers  (2024-07-11T09:56:51Z)
• AstroPT: Scaling Large Observation Models for Astronomy [0.0]
  We train a selection of foundation models of increasing size from 1 million to 2.1 billion parameters, and find that AstroPT follows a similar saturating log-log scaling law to textual models. We believe that collaborative community development paves the best route towards realising an open source Large Observation Model'
  arXiv  Detail & Related papers  (2024-05-23T18:00:00Z)
• Weak-to-Strong Extrapolation Expedites Alignment [135.12769233630362]
  We propose a method called ExPO to boost models' alignment with human preference. We demonstrate that ExPO consistently improves off-the-shelf DPO/RLHF models. We shed light on the essence of ExPO amplifying the reward signal learned during alignment training.
  arXiv  Detail & Related papers  (2024-04-25T17:39:50Z)
• AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets [7.53209156977206]
  We explore the potential of enhancing LLM performance in astronomy-focused question-answering through targeted, continual pre-training. We achieve notable improvements in specialized topic comprehension using a curated set of astronomy corpora. We present an extension of AstroLLaMA: the fine-tuning of the 7B LLaMA model on a domain-specific conversational dataset, culminating in the release of the chat-enabled AstroLLaMA for community use.
  arXiv  Detail & Related papers  (2024-01-03T04:47:02Z)
• Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning [52.29522018586365]
  We study structured pruning as an effective means to develop smaller LLMs from pre-trained, larger models. Our approach employs two key techniques: (1) targeted structured pruning, which prunes a larger model to a specified target shape by removing layers, heads, and intermediate and hidden dimensions in an end-to-end manner, and (2) dynamic batch loading, which dynamically updates the composition of sampled data in each training batch based on varying losses across different domains.
  arXiv  Detail & Related papers  (2023-10-10T15:13:30Z)
• AstroLLaMA: Towards Specialized Foundation Models in Astronomy [1.1694367694169385]
  We introduce AstroLLaMA, a 7-billion- parameter model fine-tuned from LLaMA-2 using over 300,000 astronomy abstracts from arXiv. Our model generates more insightful and scientifically relevant text completions and embedding extraction than state-of-the-arts foundation models. Its public release aims to spur astronomy-focused research, including automatic paper summarization and conversational agent development.
  arXiv  Detail & Related papers  (2023-09-12T11:02:27Z)
• Point spread function modelling for astronomical telescopes: a review focused on weak gravitational lensing studies [2.967246997200238]
  The accurate modelling of the Point Spread Function (PSF) is of paramount importance in astronomical observations. This review introduces the optical background required for a more physically-tightening PSF modelling. We provide an overview of the different physical contributors of the PSF, including the optic- and detector-level contributors and the atmosphere.
  arXiv  Detail & Related papers  (2023-06-12T19:01:50Z)
• 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)

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.