paper-with-me

Papers

ACING: Actor-Critic for Instruction Learning in Black-Box Large Language Models

2024-11-19 · Salma Kharrat, Fares Fourati, Marco Canini

The effectiveness of Large Language Models (LLMs) in solving tasks vastly depends on the quality of the instructions, which often require fine-tuning through extensive human effort. This highlights the need for automated instruction optimization; however, this optimization is particularly challenging when dealing with black-box LLMs, where model parameters and gradients remain inaccessible. We propose ACING, a task-specific prompt optimization approach framed as a stateless continuous-action Reinforcement Learning (RL) problem, known as the continuum bandit setting. ACING leverages an actor-critic-based method to optimize prompts, learning from non-differentiable reward signals. We validate ACING by optimizing prompts for ChatGPT on 30 instruction-based tasks. ACING consistently outperforms baseline methods, achieving a median score improvement of 10 percentage points. Furthermore, ACING not only recovers but also surpasses human-crafted expert instructions, achieving up to a 39 percentage point improvement against human benchmarks.

📄 PDF Abstract BibTeX arXiv:2411.12736

Code (1)

salmakh1/ACING 공식 구현 pytorch

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions

2024-03-14 · Hao Zhang, Wenqi Shao, Hong Liu, Yongqiang Ma 외

Large Vision-Language Models (LVLMs) have shown significant progress in responding well to visual-instructions from users. However, these instructions, encompassing images and text, are susceptible to both intentional an…

FairnessLanguage ModelingLanguage Modelling

CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment

2023-10-25 · Jixiang Hong, Quan Tu, Changyu Chen, Xing Gao 외

Language models trained on large-scale corpus often generate content that is harmful, toxic, or contrary to human preferences, making their alignment with human values a critical concern. Reinforcement learning from huma…

In-Context LearningInstruction FollowingLanguage ModellingPseudo Label

Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

2023-12-21 · Jingwei Yi, Yueqi Xie, Bin Zhu, Emre Kiciman 외

The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection attacks. In these attacks, malicious inst…

Benchmarking

Who Taught You That? Tracing Teachers in Model Distillation

2025-02-10 · Somin Wadhwa, Chantal Shaib, Silvio Amir, Byron C. Wallace

Model distillation -- using outputs from a large teacher model to teach a small student model -- is a practical means of creating efficient models for a particular task. We ask: Can we identify a students' teacher based …

Instruction FollowingPOSQuestion Answering

InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models

2023-06-05 · Lichang Chen, Jiuhai Chen, Tom Goldstein, Heng Huang 외

Large language models~(LLMs) are instruction followers, but it can be challenging to find the best instruction for different situations, especially for black-box LLMs on which backpropagation is forbidden. Instead of dir…

Bayesian Optimization