Papers
Topics
Authors
Recent
Search
2000 character limit reached

CourseGPT-zh: an Educational Large Language Model Based on Knowledge Distillation Incorporating Prompt Optimization

Published 8 May 2024 in cs.CL | (2405.04781v1)

Abstract: LLMs have demonstrated astonishing capabilities in NLP tasks, sparking interest in their application to professional domains with higher specialized requirements. However, restricted access to closed-source LLMs via APIs and the difficulty in collecting massive high-quality datasets pose obstacles to the development of LLMs in education fields of various courses. Given these challenges, we propose CourseGPT-zh, a course-oriented education LLM that supports customization and low-cost deployment. To address the comprehensiveness and diversity requirements of course-specific corpora, we design a high-quality question-answering corpus distillation framework incorporating prompt optimization, which effectively mines textbook knowledge and enhances its diversity. Moreover, considering the alignment of LLM responses with user needs, a novel method for discrete prompt optimization based on LLM-as-Judge is introduced. During optimization, this framework leverages the LLM's ability to reflect on and exploit error feedback and patterns, allowing for prompts that meet user needs and preferences while saving response length. Lastly, we obtain CourseGPT-zh based on the open-source LLM using parameter-efficient fine-tuning. Experimental results show that our discrete prompt optimization framework effectively improves the response quality of ChatGPT, and CourseGPT-zh exhibits strong professional capabilities in specialized knowledge question-answering, significantly outperforming comparable open-source models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. OpenAI ChatGPT. optimizing language models for dialogue. openai. 2022, 2023.
  2. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
  3. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
  4. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414, 2022.
  5. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682, 2022.
  6. Larger language models do in-context learning differently. arXiv preprint arXiv:2303.03846, 2023.
  7. Abulhair Saparov and He He. Language models are greedy reasoners: A systematic formal analysis of chain-of-thought. arXiv preprint arXiv:2210.01240, 2022.
  8. Educhat: A large-scale language model-based chatbot system for intelligent education. arXiv preprint arXiv:2308.02773, 2023.
  9. Xiezhi: An ever-updating benchmark for holistic domain knowledge evaluation. arXiv preprint arXiv:2306.05783, 2023.
  10. Medagents: Large language models as collaborators for zero-shot medical reasoning. arXiv preprint arXiv:2311.10537, 2023.
  11. Can generalist foundation models outcompete special-purpose tuning? case study in medicine. arXiv preprint arXiv:2311.16452, 2023.
  12. Medchatzh: a better medical adviser learns from better instructions. arXiv preprint arXiv:2309.01114, 2023.
  13. Xuanyuan 2.0: A large chinese financial chat model with hundreds of billions parameters. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pages 4435–4439, 2023.
  14. Bloom: A 176b-parameter open-access multilingual language model. 2022.
  15. Chatlaw: Open-source legal large language model with integrated external knowledge bases. arXiv preprint arXiv:2306.16092, 2023.
  16. Fingpt: Open-source financial large language models. arXiv preprint arXiv:2306.06031, 2023.
  17. C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models. Advances in Neural Information Processing Systems, 36, 2024.
  18. Agieval: A human-centric benchmark for evaluating foundation models. arXiv preprint arXiv:2304.06364, 2023.
  19. Cmmlu: Measuring massive multitask language understanding in chinese. arXiv preprint arXiv:2306.09212, 2023.
  20. Owl: A large language model for it operations. arXiv preprint arXiv:2309.09298, 2023.
  21. Geoglue: A geographic language understanding evaluation benchmark. arXiv preprint arXiv:2305.06545, 2023.
  22. Not all languages are created equal in llms: Improving multilingual capability by cross-lingual-thought prompting. arXiv preprint arXiv:2305.07004, 2023.
  23. Extrapolating large language models to non-english by aligning languages. arXiv preprint arXiv:2308.04948, 2023.
  24. Training language models to follow instructions with human feedback. Advances in neural information processing systems, 35:27730–27744, 2022.
  25. Mixtral of experts. arXiv preprint arXiv:2401.04088, 2024.
  26. Huatuogpt, towards taming language model to be a doctor. arXiv preprint arXiv:2305.15075, 2023.
  27. Gpt understands, too. AI Open, 2023.
  28. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837, 2022.
  29. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190, 2021.
  30. P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602, 2021.
  31. Connecting large language models with evolutionary algorithms yields powerful prompt optimizers. arXiv preprint arXiv:2309.08532, 2023.
  32. Large language models are human-level prompt engineers. arXiv preprint arXiv:2211.01910, 2022.
  33. Large language models as optimizers. arXiv preprint arXiv:2309.03409, 2023.
  34. Promptagent: Strategic planning with language models enables expert-level prompt optimization. arXiv preprint arXiv:2310.16427, 2023.
  35. Self-instruct: Aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560, 2022.
  36. Warm: On the benefits of weight averaged reward models. arXiv preprint arXiv:2401.12187, 2024.
  37. Odin: Disentangled reward mitigates hacking in rlhf. arXiv preprint arXiv:2402.07319, 2024.
  38. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems, 36, 2024.
  39. Alignbench: Benchmarking chinese alignment of large language models. arXiv preprint arXiv:2311.18743, 2023.
  40. Reflexion: Language agents with verbal reinforcement learning.(2023). arXiv preprint cs.AI/2303.11366, 2023.
  41. Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. arXiv preprint arXiv:2305.02301, 2023.
  42. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021.
  43. Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation. arXiv preprint arXiv:2107.02137, 2021.
  44. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318, 2002.
  45. Gleu: Automatic evaluation of sentence-level fluency. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 344–351, 2007.
  46. Chin-Yew Lin. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74–81, 2004.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free