mlsanityData to 14 Oct 2026

Mockingbird: How does LLM perform in general machine learning tasks?

arXiv 2508.04279 ↗First posted 6 Aug 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are now being used with increasing frequency as chat bots, tasked with the summarizing information or generating text and code in accordance with user instructions. The rapid increase in reasoning capabilities and inference speed of LLMs has revealed their remarkable potential for applications extending beyond the domain of chat bots to general machine learning tasks. This work is conducted out of the curiosity about such potential. In this work, we propose a framework Mockingbird to adapt LLMs to general machine learning tasks and evaluate its performance and scalability on several general machine learning tasks. The core concept of this framework is instructing LLMs to role-play functions and reflect on its mistakes to improve itself. Our evaluation and analysis result shows that LLM-driven machine learning methods, such as Mockingbird, can achieve acceptable results on common machine learning tasks; however, solely reflecting on its own currently cannot outperform the effect of domain-specific documents and feedback from human experts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 6 Aug 2025.

Builds on

29 of 43 references.

References · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  3. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  4. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  5. 2024The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructionscited by 493
  6. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  7. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 366
  8. 2022Data Distributional Properties Drive Emergent In-Context Learning in Transformerscited by 309
  9. 2023Role-Play with Large Language Modelscited by 294
  10. 2023In-context Autoencoder for Context Compression in a Large Language Modelcited by 199
  11. 2023Is Self-Repair a Silver Bullet for Code Generation?cited by 197
  12. 2022Active Example Selection for In-Context Learningcited by 196
17 more
  1. 2023What Makes Good Examples for Visual In-Context Learning?cited by 150
  2. 2023Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineeringcited by 127
  3. 2024DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoningcited by 125
  4. 2022General-Purpose In-Context Learning by Meta-Learning Transformerscited by 105
  5. 2024LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBenchcited by 94
  6. 2023In-Context Learning with Iterative Demonstration Selectioncited by 74
  7. 2023ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Codecited by 65
  8. 2023Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functionscited by 63
  9. 2023In-context Example Selection with Influencescited by 61
  10. 2024Revisiting Demonstration Selection Strategies in In-Context Learningcited by 58
  11. 2024Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inferencecited by 53
  12. 2023In-Context Learning Learns Label Relationships but Is Not Conventional Learningcited by 51
  13. 2024LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluationcited by 49
  14. 2024Effectively Compress KV Heads for LLMcited by 30
  15. 2024Adapting LLMs for Efficient Context Processing through Soft Prompt Compressioncited by 22
  16. 2023In-Context Learning Dynamics with Random Binary Sequencescited by 13
  17. 2024In-Context Learning Demonstration Selection via Influence Analysiscited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025LLMs as In-Context Meta-Learners for Model and Hyperparameter Selection
  2. 2024ChatGPT Alternative Solutions: Large Language Models Survey
  3. 2025Large Language Models as Universal Predictors? An Empirical Study on Small Tabular Datasets
  4. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
  5. 2023Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages
  6. 2026Can LLM Reasoning Be Trusted? A Comparative Study: Using Human Benchmarking on Statistical Tasks
  7. 2025Domain Specific Benchmarks for Evaluating Multimodal Large Language Models
  8. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback