按年被提到
20242024 · 1 次2026
大模型与语言模型›大模型推理与思维链·arXiv:2407.11373 · cs.CL

Reliable Reasoning Beyond Natural Language

Nasim Borazjanizadeh, Steven T. Piantadosi · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-07-19 · 最近 2025-05-22
2不同的人
2活跃月份
2讨论串
11被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Despite their linguistic competence, Large Language Models (LLMs) often struggle to reason reliably and flexibly. To identify these shortcomings, we introduce the Non-Linear Reasoning (NLR) dataset, a collection of 55 unique, hand-designed problems that target reasoning bottlenecks arising from the sequential prediction paradigm of LLMs and the inherently linear nature of natural language. NLR tasks require iterative updates, backtracking, and reasoning across multiple parallel chains of thought but only basic arithmetic to solve. To address these limitations, we propose a neurosymbolic reasoning approach that integrates Prolog, a symbolic reasoning engine, into the inference pipeline of LLMs. This division of labor shifts the LLM's task from iterative computations to inferring all information, explicit or implied through common sense, and encoding it as logical code. Our method yields large and robust performance gains across the GSM8k and BIG-bench Navigate benchmarks and achieves near-perfect accuracy on NLR problems, maintaining robustness even as variable interdependence - the number of other variables on which the value of a single variable depends - increases.

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arunbahl · 2025-05

“Awesome stuff! We use a similar approach (without MCP) to great effect with Prolog currently and feels like we're only just starting to scratch the surface here. A great paper from Nasim Borazjanizadeh and Steven Piantadosi at UC Berkeley for those interested: Reliable Reasoning Beyond Natural Language https://arxiv.org/abs/2407.11373 For anyone digging…”

Adventures in Symbolic Algebra with Model Context Protocol原评论 ↗
被提交为 story · 1 次