large language models

Artifacts of "Grounding Large Language Models in a Symbolic Formalization Environment for Natural-Language Planning"

Experimental results for the paper "Grounding Large Language Models in a Symbolic Formalization Environment for Natural-Language Planning". The archive contains the results of 5,100 formalization sessions. Qwen 3.5 (122B) and GPT-OSS (120B) each formalized the 2,550 Blocksworld, Logistics and Rovers problems of the ben...

Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways

Third-party Large Language Model (LLM) API gateways are rapidly emerging as unified access points to models offered by multiple vendors. However, the internal routing, caching, and billing policies of these gateways are largely undisclosed, leaving users with limited visibility into whether requests are served by the a...

Acoustic recognition of tilapia feeding intensity via LoRA-fine-tuned multimodal large language models

c as the Ball of Velocity Space ── 2nd ed.: This Was a Result About c, Not About 4 pi (the Yamagishi Patch and Thomas Precession) ── [Paper 60]

c as the Ball of Velocity Space — second edition: this was a result about c, not about four pi. In special relativity the set of admissible velocities is a ball of radius c, and under the metric induced by the velocity-addition law it is hyperbolic space of curvature minus one over c squared (Varicak 1910). Here the re...

Comparing the Marking Accuracy of an AI Marking System with Official Examination Board Marks and Experienced Teacher Judgement A Case Study in GCSE Physics

Automated marking systems built on large language models are increasingly proposed as a way toreduce teacher workload and to provide fast, formative feedback on examination-style questions.Before such systems can be trusted for either formative or summative use, however, their markingaccuracy needs to be quantified aga...

Innovative Application of Drilling Engineering Data Quality Control Based on Generative Artificial Intelligence Technology

Abstract Innovative achievements of quality inspection in data government science applications based on digital technology will provide data guarantee for the construction of oil and gas production and operations. To provide intelligent application support for the quality inspection of massive and diverse data formats...

Sistem Pendukung Keputusan Aset TI Berbasis LLM dengan Guardrail Domain

Manajemen aset Teknologi Informasi (TI) memerlukan keputusan yang dapat dipertanggungjawabkan berdasarkan data aset, riwayat pemeliharaan, kebutuhan pengguna, dan data monitoring. Penelitian ini mengusulkan sistem pendukung keputusan aset TI yang mengintegrasikan large language model, aturan guardrail domain, dan verif...

Speech-guided unmanned aerial vehicle control system based on large language model-structured execution graphs with expert rule constraints

Mapping the RAG landscape: a four-axis taxonomy of efficiency, defense, interactivity, and reasoning

Large Language Models (LLMs) have demonstrated remarkable fluency across many tasks but remain limited by their static, parameter-bound knowledge and their susceptibility to hallucinating information. Retrieval-Augmented Generation (RAG) addresses these issues by incorporating external retrieval into the generation pro...

The Prison of Syntax? The Chinese Room, Contemporary AI, and the Limits of What We Can Rule Out

Abstract This essay examines the scope of John Searle's Chinese room argument in light of trained neural networks and large language models. Its central claim is that the argument alone does not justify ruling out artificial understanding in general, and that assessments of phenomenal consciousness require further argu...

The ABC Conjecture Is a Theorem for Polynomials and a Conjecture for Integers: Integers Lack the Derivative ── for polynomials maxdeg never exceeds the number of distinct roots minus 1 (the Mason--Stothers theorem), so the same inequality never fails ── its proof uses that the Wronskian ab'-a'b is divisible by the repeated part of the roots, and integers have no such derivative ── [Paper 641]

For coprime positive integers a+b=c, write rad(abc) for the product of the distinct primes dividing abc, and define the quality q=log c/lograd(abc). The ABC conjecture says that for every epsilon>0 only finitely many triples have q>1+epsilon. The same question can be posed for polynomials, where it is a theorem. This p...

"Rare" Is Measured on a Logarithmic Scale ── The Central Limit Theorem Is the Wrong Instrument in the Tail, and the Fence Is the Single Big Jump ── [Paper 190]

When an event is called extremely rare, the next question is on what scale it was measured. When a probability falls through orders of magnitude, saying how many times larger one thing is than another stops meaning anything. This paper shows, against exact combinatorial values, that the right scale for a rare event is...