paper-with-me

홈 › Papers

Retcon -- a Prompt-Based Technique for Precise Control of LLMs in Conversations

2026-02-09 · David Kogan, Sam Nguyen, Masanori Suzuki, Feiyang Chen arxiv

Recent advances in Large Language Models (LLMs) allow agents to execute complex natural language tasks. Many LLM applications, such as support agents, teaching assistants, and interactive bots, involve multi-turn conversations. However, it remains challenging to control LLMs in the context of such interactions, particularly when the LLM behavior needs to be adjustable over the course of the conversation. In this paper, we present Retcon, a few-shot prompting technique designed to provide turn-level control over LLMs in conversations. We then demonstrate that it performs significantly better than zero-shot and traditional few-shot prompting.

📄 PDF Abstract BibTeX arXiv:2603.03317

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Plan-and-Write: Structure-Guided Length Control for LLMs without Model Retraining

2025-11-03 · Adewale Akinfaderin, Shreyas Subramanian, Akarsha Sehwag arxiv

Length control in Large Language Models (LLMs) is a crucial but under-addressed challenge, with applications ranging from voice interfaces requiring concise responses to research summaries needing comprehensive outputs. …

Document SummarizationPrompt Engineering

Universal and Context-Independent Triggers for Precise Control of LLM Outputs

2024-11-22 · Jiashuo Liang, Guancheng Li, Yang Yu

Large language models (LLMs) have been widely adopted in applications such as automated content generation and even critical decision-making systems. However, the risk of prompt injection allows for potential manipulatio…

Decision Making

Controlled Text Generation via Language Model Arithmetic

2023-11-24 · Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner, Martin Vechev

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 fo…

Language ModelingLanguage ModellingmodelText Generation

A Mixture of Linear Corrections Generates Secure Code

2025-07-13 · Weichen Yu, Ravi Mangal, Terry Zhuo, Matt Fredrikson 외 arxiv

Large language models (LLMs) have become proficient at sophisticated code-generation tasks, yet remain ineffective at reliably detecting or avoiding code vulnerabilities. Does this deficiency stem from insufficient learn…

Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning

2026-04-07 · Yanbei Jiang, Amr Keleg, Ryandito Diandaru, Jey Han Lau 외 arxiv

While the real world is inherently stochastic, Large Language Models (LLMs) are predominantly evaluated on single-round inference against fixed ground truths. In this work, we shift the lens to distribution alignment: as…

Prompt Engineering