Large Language Models Are Self-Taught Reasoners: Enhancing LLM Applications via Tailored Problem-Solving Demonstrations
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
Guiding large language models with a selected set of human-authored demonstrations is a common practice for improving LLM applications. However, human effort can be costly, especially in specialized domains (e.g., clinical diagnosis), and does not guarantee optimal performance due to the potential discrepancy of target skills between selected demonstrations and real test instances. Motivated by these, this paper explores the automatic creation of customized demonstrations, whose target skills align with the given target instance. We present SELF-TAUGHT, a problem-solving framework, which facilitates demonstrations that are "tailored" to the target problem and "filtered" for better quality (i.e., correctness) in a zero-shot manner. In 15 tasks of multiple-choice questions of diverse domains and the diagnosis of Alzheimer's disease (AD) with real-world patients, SELF-TAUGHT achieves superior performance to strong baselines (e.g., Few-shot CoT, Plan-and-Solve, Auto-CoT). We conduct comprehensive analyses on SELF-TAUGHT, including its generalizability to existing prompting methods and different LLMs, the quality of its intermediate generation, and more.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 14 of its 44 references that are in the map. First posted on arXiv 22 Aug 2024.
Builds on
14 of 44 references.
Closest ancestors · 2
Same direction, newest first
- 2024Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models27 Feb
- 2023Better Zero-Shot Reasoning with Role-Play Prompting15 Aug
Other references · 12
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2020Measuring Massive Multitask Language Understandingcited by 7,768
- 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
- 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
- 2024BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domainscited by 299
- 2024Self-Discover: Large Language Models Self-Compose Reasoning Structurescited by 108
- 2022Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrationscited by 70
- 2022Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generatorcited by 68
- 2024LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillationcited by 32
- 2024Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewardscited by 31
- 2024Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Modelscited by 20
- 2024Integrating Chemistry Knowledge in Large Language Models via Prompt Engineeringcited by 10
Built on by
Citing papers per year: 2024: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2023Teaching Language Models to Self-Improve through Interactive Demonstrations
- 2025Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving
- 2026Not the Example, but the Process: How Self-Generated Examples Enhance LLM Reasoning
- 2022Large Language Models Can Self-Improve
- 2024Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
- 2023AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations
- 2025Self-Training Large Language Models for Tool-Use Without Demonstrations
- 2025Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation