# In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement

arXiv: https://arxiv.org/abs/2410.03124 · HTML: https://mlsanity.com/paper/2410.03124/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 41 references that are in the map.
- First posted on arXiv 4 Oct 2024.

## Builds on (most cited first, 30 of 31)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection](https://mlsanity.com/paper/2306.04637/) (2023)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning](https://mlsanity.com/paper/2312.01552/) (2023)
- [Black-Box Tuning for Language-Model-as-a-Service](https://mlsanity.com/paper/2201.03514/) (2022)
- [Black-Box Prompt Optimization: Aligning Large Language Models without Model Training](https://mlsanity.com/paper/2311.04155/) (2023)
- [Black-box Prompt Learning for Pre-trained Language Models](https://mlsanity.com/paper/2201.08531/) (2022)
- [Better Zero-Shot Reasoning with Self-Adaptive Prompting](https://mlsanity.com/paper/2305.14106/) (2023)
- [LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback](https://mlsanity.com/paper/2311.09336/) (2023)
- [DOCKSTRING: easy molecular docking yields better benchmarks for ligand design](https://mlsanity.com/paper/2110.15486/) (2021)
- [Human-Instruction-Free LLM Self-Alignment with Limited Samples](https://mlsanity.com/paper/2401.06785/) (2024)
- [Universal Self-Adaptive Prompting](https://mlsanity.com/paper/2305.14926/) (2023)

## Built on by (most cited first, 1 of 1)

- [LProtector: An LLM-driven Vulnerability Detection System](https://mlsanity.com/paper/2411.06493/) (2024)

## Abstract (arXiv)

Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality. Most existing methods rely on human supervision or parameter retraining, both of which are costly in terms of data collection and computational resources. To handle these challenges, a direct solution is to generate ``high-confidence'' data from unsupervised downstream tasks and use them for in-context prompting or prompt optimization to refine the pseudo-supervision. However, relying solely on such data may lead to overfitting. In this paper, we leverage the in-context learning (ICL) abilities of LLMs and propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision. The proposed learning objective ensures that the optimized prompt guides the LLM to generate consistent responses for a given input when pseudo-supervised data from the downstream task are used as demonstrations, enabling refinement over the entire pseudo-supervision. The prompt is optimized by translating gradient signals into textual critiques, which serve as feedback to iteratively refine the prompt and model responses. Theoretical analysis in a simplified classification setting shows that the refined pseudo-supervision exhibits a geometric clustering structure, helping to mitigate overfitting. Experiments on question answering, natural language inference benchmarks, and a real-world molecule optimization task, show the effectiveness of the proposed algorithm.