中文
相关论文

相关论文: Syntactic and Semantic Control of Large Language M…

200 篇论文

Text-to-SQL generation enables non-experts to interact with databases via natural language. Recent advances rely on large closed-source models like GPT-4 that present challenges in accessibility, privacy, and latency. To address these…

Despite recent advances in large language models, open-source models often struggle to consistently perform well on complex reasoning tasks. Existing ensemble methods, whether applied at the token or output levels, fail to address these…

计算与语言 · 计算机科学 2024-12-23 Sungjin Park , Xiao Liu , Yeyun Gong , Edward Choi

This paper proposes a synergy of amortised and particle-based methods for sampling from distributions defined by unnormalised density functions. We state a connection between sequential Monte Carlo (SMC) and neural sequential samplers…

机器学习 · 计算机科学 2025-10-14 Sanghyeok Choi , Sarthak Mittal , Víctor Elvira , Jinkyoo Park , Nikolay Malkin

Large language models (LLMs) can be used to support software development tasks, e.g., through code completion or code generation. However, their effectiveness drops significantly when considering less popular programming languages such as…

软件工程 · 计算机科学 2026-03-06 David Delgado , Lola Burgueño , Robert Clarisó

We propose sequential Monte Carlo (SMC) methods for sampling the posterior distribution of state-space models under highly informative observation regimes, a situation in which standard SMC methods can perform poorly. A special case is…

统计计算 · 统计学 2015-07-10 Pierre Del Moral , Lawrence M. Murray

Recent work has shown that energy-based language modeling is an effective framework for controllable text generation because it enables flexible integration of arbitrary discriminators. However, because energy-based LMs are globally…

计算与语言 · 计算机科学 2023-12-08 Jarad Forristal , Niloofar Mireshghallah , Greg Durrett , Taylor Berg-Kirkpatrick

An effective approach for sampling from unnormalized densities is based on the idea of gradually transporting samples from an easy prior to the complicated target distribution. Two popular methods are (1) Sequential Monte Carlo (SMC), where…

Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired…

计算与语言 · 计算机科学 2024-10-07 Lifu Tu , Semih Yavuz , Jin Qu , Jiacheng Xu , Rui Meng , Caiming Xiong , Yingbo Zhou

We propose a novel sequential Monte Carlo (SMC) method for sampling from unnormalized target distributions based on a reverse denoising diffusion process. While recent diffusion-based samplers simulate the reverse diffusion using…

统计计算 · 统计学 2025-11-06 Luhuan Wu , Yi Han , Christian A. Naesseth , John P. Cunningham

Sequential Monte Carlo (SMC) methods have recently shown successful results for conditional sampling of generative diffusion models. In this paper we propose a new diffusion posterior SMC sampler achieving improved statistical efficiencies,…

机器学习 · 统计学 2025-08-25 Zheng Zhao

Language models (LMs) can generate code but cannot guarantee its correctness$\unicode{x2014}$often producing outputs that violate type safety, program invariants, or other semantic properties. Constrained decoding offers a solution by…

编程语言 · 计算机科学 2025-12-03 Shaan Nagy , Timothy Zhou , Nadia Polikarpova , Loris D'Antoni

NoSQL databases have been widely adopted in big data analytics, geospatial applications, and healthcare services, due to their flexibility and scalability. However, querying NoSQL databases requires specialized technical expertise, creating…

数据库 · 计算机科学 2026-02-16 Xubang Xiong , Raymond Chi-Wing Wong , Yuanfeng Song

Symbolic regression is a powerful tool for discovering governing equations directly from data, but its sensitivity to noise hinders its broader application. This paper introduces a Sequential Monte Carlo (SMC) framework for Bayesian…

机器学习 · 计算机科学 2025-12-12 Geoffrey F. Bomarito , Patrick E. Leser

Self-consistency (SC) is a widely used test-time inference technique for improving performance in chain-of-thought reasoning. It involves generating multiple responses, or samples from a large language model (LLM) and selecting the most…

机器学习 · 计算机科学 2025-11-18 Austin Feng , Marius Alonso , Ambroise Odonnat

Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning…

人工智能 · 计算机科学 2025-01-14 Amr Almorsi , Mohanned Ahmed , Walid Gomaa

Controllable and transparent text generation has been a long-standing goal in NLP. Almost as long-standing is a general idea for addressing this challenge: Parsing text to a symbolic representation, and generating from it. However, earlier…

计算与语言 · 计算机科学 2025-11-25 Hongji Li , Andrianos Michail , Reto Gubelmann , Simon Clematide , Juri Opitz

Enhancing large language models by simply scaling up datasets has begun to yield diminishing returns, shifting the spotlight to data quality. Monte Carlo Tree Search (MCTS) has emerged as a powerful technique for generating high-quality…

人工智能 · 计算机科学 2025-06-10 Yanwei Ren , Haotian Zhang , Fuxiang Wu , Jiayan Qiu , Jiaxing Huang , Baosheng Yu , Liu Liu

Multi-agent systems built on large language models (LLMs) are difficult to reason about. Coordination errors such as deadlocks or type-mismatched messages are often hard to detect through testing. We introduce a domain-specific language for…

编程语言 · 计算机科学 2026-04-30 Benedikt Bollig , Matthias Függer , Thomas Nowak

As large-scale language model pretraining pushes the state-of-the-art in text generation, recent work has turned to controlling attributes of the text such models generate. While modifying the pretrained models via fine-tuning remains the…

计算与语言 · 计算机科学 2021-08-05 Sachin Kumar , Eric Malmi , Aliaksei Severyn , Yulia Tsvetkov

It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition. We introduce Click for controllable text generation,…

计算与语言 · 计算机科学 2023-06-07 Chujie Zheng , Pei Ke , Zheng Zhang , Minlie Huang
‹ 上一页 1 8 9 10 下一页 ›