paper-with-me

홈 › Papers

A Categorical Analysis of Large Language Models and Why LLMs Circumvent the Symbol Grounding Problem

2025-12-09 · Luciano Floridi, Yiyang Jia, Fernando Tohmé arxiv

This paper presents a formal, categorical framework for analysing how humans and large language models (LLMs) transform content into truth-evaluated propositions about a state space of possible worlds W , in order to argue that LLMs do not solve but circumvent the symbol grounding problem.

📄 PDF Abstract BibTeX arXiv:2512.09117

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Categorical Syllogisms Revisited: A Review of the Logical Reasoning Abilities of LLMs for Analyzing Categorical Syllogism

2024-06-26 · Shi Zong, Jimmy Lin

There have been a huge number of benchmarks proposed to evaluate how large language models (LLMs) behave for logic inference tasks. However, it remains an open question how to properly evaluate this ability. In this pape…

Logical Reasoning

A Rose by Any Other Name Would Smell as Sweet: Categorical Homotopy Theory for Large Language Models

2025-08-07 · Sridhar Mahadevan arxiv

Natural language is replete with superficially different statements, such as ``Charles Darwin wrote" and ``Charles Darwin is the author of", which carry the same meaning. Large language models (LLMs) should generate the …

Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQL

2026-04-10 · Vishnu Murali, Anmol Gulati, Elias Lumer, Kevin Frank 외 arxiv

Translating natural language into Jira Query Language (JQL) requires resolving ambiguous field references, instance-specific categorical values, and complex Boolean predicates. Single-pass LLMs cannot discover which cate…

Semantic Retrieval

Categorical Perception in Large Language Model Hidden States: Structural Warping at Digit-Count Boundaries

2026-03-30 · Jon-Paul Cacioli arxiv

Categorical perception (CP) -- enhanced discriminability at category boundaries -- is among the most studied phenomena in perceptual psychology. This paper reports that analogous geometric warping occurs in the hidden-st…

Beyond Context: Large Language Models' Failure to Grasp Users' Intent

2025-12-24 · Ahmed M. Hussain, Salahuddin Salahuddin arxiv

Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability to understand context and recognize user intent. This creates exploitab…

Intent RecognitionIntent Detection