中文
相关论文

相关论文: From Natural Language to Executable Narsese: A Neu…

200 篇论文

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…

计算与语言 · 计算机科学 2025-12-02 Nasim Borazjanizadeh , Steven T. Piantadosi

Large language models (LLMs) often struggle to perform multi-target reasoning in long-context scenarios where relevant information is scattered across extensive documents. To address this challenge, we introduce NeuroSymbolic Augmented…

计算与语言 · 计算机科学 2025-06-04 Sina Bagheri Nezhad , Ameeta Agrawal

Non-Axiomatic Reasoning Systems (NARS) provide a framework for building adaptive agents that operate under insufficient knowledge and resources. However, the standard input language, Narsese, poses a usability barrier: its dense symbolic…

编程语言 · 计算机科学 2026-04-02 Seamus Brady

Large Language Models (LLMs) excel in complex reasoning tasks but struggle with consistent rule application, exception handling, and explainability, particularly in domains like legal analysis that require both natural language…

人工智能 · 计算机科学 2025-11-11 Albert Sadowski , Jarosław A. Chudziak

Translating formal language into natural language is a foundational challenge in NLP, driving various downstream applications in semantic parsing, theorem validation, and question answering. In this study, we introduce First-Order Logic to…

计算与语言 · 计算机科学 2026-05-19 Mei Jia

The use of formal language for deductive logical reasoning aligns well with language models (LMs), where translating natural language (NL) into first-order logic (FOL) and employing an external solver results in a verifiable and therefore…

计算与语言 · 计算机科学 2026-01-15 Ramya Keerthy Thatikonda , Jiuzhou Han , Wray Buntine , Ehsan Shareghi

Translating natural language into formal language such as First-Order Logic (FOL) is a foundational challenge in NLP with wide-ranging applications in automated reasoning, misinformation tracking, and knowledge validation. In this paper, we…

计算与语言 · 计算机科学 2025-03-07 Abhinav Lalwani , Tasha Kim , Lovish Chopra , Christopher Hahn , Zhijing Jin , Mrinmaya Sachan

Large Language Models (LLMs) have demonstrated impressive progress in complex reasoning tasks, largely driven by the Chain-of-Thought (CoT) paradigm, which decomposes difficult problems into intermediate steps. However, CoT reasoning…

符号计算 · 计算机科学 2026-05-26 Rui Wang , Zeming Wei , Yihao Zhang , Xiaokun Luan

Pre-trained large language models (LMs) struggle to perform logical reasoning reliably despite advances in scale and compositionality. In this work, we tackle this challenge through the lens of symbolic programming. We propose DSR-LM, a…

人工智能 · 计算机科学 2023-05-09 Hanlin Zhang , Jiani Huang , Ziyang Li , Mayur Naik , Eric Xing

Structured reasoning over natural language inputs remains a core challenge in artificial intelligence, as it requires bridging the gap between unstructured linguistic expressions and formal logical representations. In this paper, we propose…

人工智能 · 计算机科学 2025-07-14 Keying Yang , Hao Wang , Kai Yang

Neural-symbolic methods have demonstrated efficiency in enhancing the reasoning abilities of large language models (LLMs). However, existing methods mainly rely on syntactically mapping natural languages to complete formal languages like…

计算与语言 · 计算机科学 2024-06-04 Yiming Wang , Zhuosheng Zhang , Pei Zhang , Baosong Yang , Rui Wang

Large Language Models (LLMs) still struggle with complex logical reasoning. While previous works achieve remarkable improvements, their performance is highly dependent on the correctness of translating natural language (NL) problems into a…

人工智能 · 计算机科学 2025-10-14 Xiangyu Wang , Haocheng Yang , Fengxiang Cheng , Fenrong Liu

Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical inconsistencies, and sharp performance degradation on high-complexity problems. While…

人工智能 · 计算机科学 2026-05-01 Adam Ishay , Joohyung Lee

A persistent challenge in AI is the effective integration of material and formal inference - the former concerning the plausibility and contextual relevance of arguments, while the latter focusing on their logical and structural validity.…

人工智能 · 计算机科学 2025-04-08 Xin Quan , Marco Valentino , Danilo S. Carvalho , Dhairya Dalal , André Freitas

State-of-the-art models in NLP are now predominantly based on deep neural networks that are opaque in terms of how they come to make predictions. This limitation has increased interest in designing more interpretable deep models for NLP…

计算与语言 · 计算机科学 2020-04-27 Jay DeYoung , Sarthak Jain , Nazneen Fatema Rajani , Eric Lehman , Caiming Xiong , Richard Socher , Byron C. Wallace

In recent years, neuro-symbolic methods have become a popular and powerful approach that augments artificial intelligence systems with the capability to perform abstract, logical, and quantitative deductions with enhanced precision and…

人工智能 · 计算机科学 2025-02-04 Yuxuan Wu , Hideki Nakayama

Large language models (LLMs) and theorem provers (TPs) can be effectively combined for verifiable natural language inference (NLI). However, existing approaches rely on a fixed logical formalism, a feature that limits robustness and…

人工智能 · 计算机科学 2026-01-12 Ali Farjami , Luca Redondi , Marco Valentino

Recent advances in large language models (LLMs) have significantly enhanced question-answering (QA) capabilities, particularly in open-domain contexts. However, in closed-domain scenarios such as education, healthcare, and law, users demand…

计算与语言 · 计算机科学 2025-07-29 Tuan Bui , Trong Le , Phat Thai , Sang Nguyen , Minh Hua , Ngan Pham , Thang Bui , Tho Quan

Clinical decision-making requires reasoning over incomplete, imprecise, and linguistically expressed patient narratives. While large language models (LLMs) excel at extracting latent information from natural language, they lack the…

人工智能 · 计算机科学 2026-05-26 Xiaoyang Fan , Yufan Cai , Zhe Hou , Jin Song Dong

Large Language Models (LLMs) have revolutionized natural language processing, yet they struggle with inconsistent reasoning, particularly in novel domains and complex logical sequences. This research introduces Proof of Thought, a framework…

人工智能 · 计算机科学 2024-10-24 Debargha Ganguly , Srinivasan Iyengar , Vipin Chaudhary , Shivkumar Kalyanaraman
‹ 上一页 1 2 3 10 下一页 ›