按年被提到
20232023 · 2 次2026
大模型与语言模型›大模型预训练与缩放·arXiv:2311.14479 · cs.CL

Controlled Text Generation via Language Model Arithmetic

Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner, Martin Vechev · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2023-12-09 · 最近 2024-03-12
3不同的人
2活跃月份
2讨论串
—被引(OpenAlex)
arXiv 摘要(候选层不写导读)

As Large Language Models (LLMs) are deployed more widely, customization with respect to vocabulary, style, and character becomes more important. In this work, we introduce model arithmetic, a novel inference framework for composing and biasing LLMs without the need for model (re)training or highly specific datasets. In addition, the framework allows for more precise control of generated text than direct prompting and prior controlled text generation (CTG) techniques. Using model arithmetic, we can express prior CTG techniques as simple formulas and naturally extend them to new and more effective formulations. Further, we show that speculative sampling, a technique for efficient LLM sampling, extends to our setting. This enables highly efficient text generation with multiple composed models with only marginal overhead over a single model. Our empirical evaluation demonstrates that model arithmetic allows fine-grained control of generated text while outperforming state-of-the-art on the task of toxicity reduction. We release an open source easy-to-use implementation of our framework at https://github.com/eth-sri/language-model-arithmetic.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论OcelotBane · 2023-12

“We developed a new framework that enables flexible control of generated text in language models. By combining several models and/or system prompts in one mathematical formula, it lets you tweak your style and combine model outputs with ease. A handy tool for those working with LLMs, looking for more fine-grained control of stylistic output. More details i…”

Show HN: Fine-grained stylistic control of LLMs using model arithmetic原评论 ↗
评论jay-barronville · 2023-12

“https://ar5iv.labs.arxiv.org/html/2311.14479 ← Here’s the link to the web-based version of the paper, for anyone who—like me—prefer to read arXiv papers via the web instead of downloading PDF documents.”

Show HN: Fine-grained stylistic control of LLMs using model arithmetic原评论 ↗
评论emrek1 · 2024-03

“Each of those is great, and more sophisticated strategies are being developed all the time: incorporating static analysis at inference time to ensure code is more than just syntactically correct [0]; to multi-LLM call agent-based frameworks [1]; decomposing hard tasks into many "easier" LLM tasks [2]; analyzing internal activations to identify potential h…”

Show HN: Prompts as WASM Programs原评论 ↗