REVIEW 7 cited by
Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large language models (LLMs) have shown impressive success in various applications. However, these models are often not well aligned with human intents, which calls for additional treatments on them; that is, the alignment problem. To make LLMs better follow user instructions, existing alignment methods primarily focus on further training them. However, the extra training of LLMs is usually expensive in terms of GPU computing; even worse, some LLMs are not accessible for user-demanded training, such as GPTs. In this work, we take a different perspective -- Black-Box Prompt Optimization (BPO) -- to perform alignments. The idea is to optimize user prompts to suit LLMs' input understanding, so as to best realize users' intents without updating LLMs' parameters. BPO leverages human preferences to optimize prompts, thus making it superior to LLM (e.g., ChatGPT) as a prompt engineer. Moreover, BPO is model-agnostic, and the empirical results demonstrate that the BPO-aligned ChatGPT yields a 22% increase in the win rate against its original version and 10% for GPT-4. Notably, the BPO-aligned LLMs can outperform the same models aligned by PPO and DPO, and it also brings additional performance gains when combining BPO with PPO or DPO. Code and datasets are released at https://github.com/thu-coai/BPO.
Forward citations
Cited by 7 Pith papers
-
MAGA-Bench: Machine-Augment-Generated Text via Alignment Detection Benchmark
Adding human-alignment augmentation (roleplaying, BPO, self-refine, RLDF) to machine-generated text both fools existing detectors and improves the generalization of detectors fine-tuned on it.
-
P3: Prompts Promote Prompting
Jointly optimizing system and user prompts offline, then adapting user prompts online via a fine-tuned model or retrieved examples, improves LLM benchmark scores over single-prompt optimizers.
-
CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention
CausalAbstain filters multilingual self-feedback by comparing how much it changes the model's abstention decision, improving abstention accuracy over baselines on two benchmarks.
-
Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition
Recursive generation, evaluation, and refinement of discrete prompts tunes a black-box multimodal LLM to each user, raising personalized visual emotion recognition accuracy on Affection from 40.6% to 44.9%.
-
Adaptive Plan-Execute Framework for Smart Contract Security Auditing
SmartAuditFlow claims 100% detection on a standard smart contract benchmark and all 13 tested CVEs via a plan-execute LLM workflow, though the supporting evaluation has major reproducibility and validation gaps.
-
Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings
DEEVO evolves better LLM prompts by debating outputs and selecting survivors with Elo ratings, without requiring labeled data or a hand-written fitness function.
-
When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs
A survey that classifies VLM attacks by goal and data manipulation strategy, and reviews defenses and metrics.
Discussion (0). Continue with ORCID to comment.