Self-Evolving GPT: A Lifelong Autonomous Experiential Learner
- URL: http://arxiv.org/abs/2407.08937v1
- Date: Fri, 12 Jul 2024 02:49:13 GMT
- Title: Self-Evolving GPT: A Lifelong Autonomous Experiential Learner
- Authors: Jinglong Gao, Xiao Ding, Yiming Cui, Jianbai Zhao, Hepeng Wang, Ting Liu, Bing Qin,
- Abstract summary: We design a lifelong autonomous experiential learning framework based on large language models (LLMs)
It autonomously learns and accumulates experience through experience transfer and induction, categorizing the types of input questions to select which accumulated experience to employ for them.
Experimental results on six widely used NLP datasets show that our framework performs reliably in each intermediate step and effectively improves the performance of GPT-3.5 and GPT-4.
- Score: 40.16716983217304
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: To improve the performance of large language models (LLMs), researchers have explored providing LLMs with textual task-solving experience via prompts. However, they rely on manual efforts to acquire and apply such experience for each task, which is not feasible for the growing demand for LLMs and the variety of user questions. To address this issue, we design a lifelong autonomous experiential learning framework based on LLMs to explore whether LLMs can imitate human ability for learning and utilizing experience. It autonomously learns and accumulates experience through experience transfer and induction, categorizing the types of input questions to select which accumulated experience to employ for them. Experimental results on six widely used NLP datasets show that our framework performs reliably in each intermediate step and effectively improves the performance of GPT-3.5 and GPT-4. This validates the feasibility of using LLMs to mimic human experiential learning and application capabilities. Additionally, we provide a detailed analysis of the behavior of our framework at each step.
Related papers
- I Need Help! Evaluating LLM's Ability to Ask for Users' Support: A Case Study on Text-to-SQL Generation [60.00337758147594]
We propose metrics to evaluate the trade-off between performance improvements and user burden.
Our experiments reveal that without external feedback, many LLMs struggle to recognize their need for additional support.
arXiv Detail & Related papers (2024-07-20T06:12:29Z) - A Reality check of the benefits of LLM in business [1.9181612035055007]
Large language models (LLMs) have achieved remarkable performance in language understanding and generation tasks.
This paper thoroughly examines the usefulness and readiness of LLMs for business processes.
arXiv Detail & Related papers (2024-06-09T02:36:00Z) - Experiential Co-Learning of Software-Developing Agents [83.34027623428096]
Large language models (LLMs) have brought significant changes to various domains, especially in software development.
We introduce Experiential Co-Learning, a novel LLM-agent learning framework.
Experiments demonstrate that the framework enables agents to tackle unseen software-developing tasks more effectively.
arXiv Detail & Related papers (2023-12-28T13:50:42Z) - A Large Language Model Approach to Educational Survey Feedback Analysis [0.0]
This paper assesses the potential for the large language models (LLMs) GPT-4 and GPT-3.5 to aid in deriving insight from education feedback surveys.
arXiv Detail & Related papers (2023-09-29T17:57:23Z) - ExpeL: LLM Agents Are Experiential Learners [60.54312035818746]
We introduce the Experiential Learning (ExpeL) agent to allow learning from agent experiences without requiring parametric updates.
Our agent autonomously gathers experiences and extracts knowledge using natural language from a collection of training tasks.
At inference, the agent recalls its extracted insights and past experiences to make informed decisions.
arXiv Detail & Related papers (2023-08-20T03:03:34Z) - Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond [48.70557995528463]
This guide aims to provide researchers and practitioners with valuable insights and best practices for working with Large Language Models.
We present various use cases and non-use cases to illustrate the practical applications and limitations of LLMs in real-world scenarios.
arXiv Detail & Related papers (2023-04-26T17:52:30Z) - ElitePLM: An Empirical Study on General Language Ability Evaluation of
Pretrained Language Models [78.08792285698853]
We present a large-scale empirical study on general language ability evaluation of pretrained language models (ElitePLM)
Our empirical results demonstrate that: (1) PLMs with varying training objectives and strategies are good at different ability tests; (2) fine-tuning PLMs in downstream tasks is usually sensitive to the data size and distribution; and (3) PLMs have excellent transferability between similar tasks.
arXiv Detail & Related papers (2022-05-03T14:18:10Z)
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.