中文
相关论文

相关论文: Why Prompt Optimization Works, and Why It Sometime…

200 篇论文

Despite advances in the multilingual capabilities of Large Language Models (LLMs), their performance varies substantially across different languages and tasks. In multilingual retrieval-augmented generation (RAG)-based systems, knowledge…

计算与语言 · 计算机科学 2025-08-01 Aman Gupta , Yingying Zhuang , Zhou Yu , Ziji Zhang , Anurag Beniwal

Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on perturbed data…

计算与语言 · 计算机科学 2025-04-04 Aryan Agrawal , Lisa Alazraki , Shahin Honarvar , Marek Rei

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

计算与语言 · 计算机科学 2026-03-23 Zafir Shamsi , Nikhil Chekuru , Zachary Guzman , Shivank Garg

Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising…

计算与语言 · 计算机科学 2025-09-03 Xiaomin Li , Zhou Yu , Zhiwei Zhang , Xupeng Chen , Ziji Zhang , Yingying Zhuang , Narayanan Sadagopan , Anurag Beniwal

Multimodal Large Language Models (MLLMs) are set to transform how machines process and generate human-like responses by integrating diverse modalities such as text, images, and code. Yet, effectively harnessing their capabilities hinges on…

人工智能 · 计算机科学 2025-04-15 Anwesha Mohanty , Venkatesh Balavadhani Parthasarathy , Arsalan Shahid

Finding the best way of adapting pre-trained language models to a task is a big challenge in current NLP. Just like the previous generation of task-tuned models (TT), models that are adapted to tasks via in-context-learning (ICL) are robust…

计算与语言 · 计算机科学 2023-10-23 Lucas Weber , Elia Bruni , Dieuwke Hupkes

Large language models (LLMs) have recently been employed as agents to solve sequential decision-making tasks such as Bayesian optimization and multi-armed bandits (MAB). These works usually adopt an LLM for sequential action selection by…

机器学习 · 计算机科学 2025-02-04 Mingze Kong , Zhiyong Wang , Yao Shu , Zhongxiang Dai

Large Language Models (LLMs) have become key components of modern software, with prompts acting as their de-facto programming interface. However, prompt design remains largely empirical and small mistakes can cascade into unreliable,…

软件工程 · 计算机科学 2025-09-19 Haoye Tian , Chong Wang , BoYang Yang , Lyuye Zhang , Yang Liu

Prompt optimization aims to search for effective prompts that enhance the performance of large language models (LLMs). Although existing prompt optimization methods have discovered effective prompts, they often differ from sophisticated…

人工智能 · 计算机科学 2025-07-14 Rin Ashizawa , Yoichi Hirose , Nozomu Yoshinari , Kento Uchida , Shinichi Shirakawa

As large language models (LLMs) are adopted as a fundamental component of language technologies, it is crucial to accurately characterize their performance. Because choices in prompt design can strongly influence model behavior, this design…

计算与语言 · 计算机科学 2024-07-03 Melanie Sclar , Yejin Choi , Yulia Tsvetkov , Alane Suhr

Large Language Models (LLMs) are increasingly embedded in enterprise workflows, yet their performance remains highly sensitive to prompt design. Automatic Prompt Optimization (APO) seeks to mitigate this instability, but existing approaches…

人工智能 · 计算机科学 2026-02-03 Wei Chen , Yanbin Fang , Shuran Fu , Fasheng Xu , Xuan Wei

LLM-based prompt optimization, that uses LLM-provided "textual gradients" (feedback) to refine prompts, has emerged an effective method for automatic prompt engineering. However, its scalability and stability are unclear when using more…

计算与语言 · 计算机科学 2025-11-19 Zixin Ding , Junyuan Hong , Zhan Shi , Jiachen T. Wang , Zinan Lin , Li Yin , Meng Liu , Zhangyang Wang , Yuxin Chen

This study explores the capability of Large Language Models (LLMs) to evaluate causality in causal graphs generated by conventional statistical causal discovery methods-a task traditionally reliant on manual assessment by human subject…

计算与语言 · 计算机科学 2025-04-16 Yuni Susanti , Nina Holsmoelle

Modern language models (LMs) are not robust to out-of-distribution inputs. Machine generated (``optimized'') prompts can be used to modulate LM outputs and induce specific behaviors while appearing completely uninterpretable. In this work,…

计算与语言 · 计算机科学 2025-09-04 Rimon Melamed , Lucas H. McCabe , H. Howie Huang

Numerous recent works aim to enhance the efficacy of Large Language Models (LLMs) through strategic prompting. In particular, the Optimization by PROmpting (OPRO) approach provides state-of-the-art performance by leveraging LLMs as…

计算与语言 · 计算机科学 2024-07-22 Tuo Zhang , Jinyue Yuan , Salman Avestimehr

Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated with chain of thought prompting-a method of demonstrating solution…

人工智能 · 计算机科学 2025-03-13 Kaya Stechly , Karthik Valmeekam , Subbarao Kambhampati

Leveraging large language models (LLMs) for complex natural language tasks typically requires long-form prompts to convey detailed requirements and information, which results in increased memory usage and inference costs. To mitigate these…

计算与语言 · 计算机科学 2024-10-18 Zongqian Li , Yinhong Liu , Yixuan Su , Nigel Collier

Prompt sensitivity, referring to the phenomenon where paraphrasing (i.e., repeating something written or spoken using different words) leads to significant changes in large language model (LLM) performance, has been widely accepted as a…

计算与语言 · 计算机科学 2025-09-03 Andong Hua , Kenan Tang , Chenhe Gu , Jindong Gu , Eric Wong , Yao Qin

Recent works on large language models (LLMs) have demonstrated the impact of prompting strategies and fine-tuning techniques on their reasoning capabilities. Yet, their effectiveness on clinical natural language inference (NLI) remains…

计算与语言 · 计算机科学 2025-07-08 Mael Jullien , Marco Valentino , Leonardo Ranaldi , Andre Freitas

Automated optimization modeling via Large Language Models (LLMs) has emerged as a promising approach to assist complex human decision-making. While post-training has become a pivotal technique to enhance LLMs' capabilities in this domain,…

机器学习 · 计算机科学 2026-02-13 Weiting Liu , Han Wu , Yufei Kuang , Xiongwei Han , Tao Zhong , Jianfeng Feng , Wenlian Lu