Skip to content

Category

small language model

2,925 papers

#small language model Open access Sep 2026

Which Publications Do AI Assistants Cite When Recommending Businesses? An Exploratory Study

Consumers increasingly ask conversational large language models (LLMs) which product or company to choose. When web-search-enabled assistants answer, they ground their recommendations in sources retrieved at query time, yet little is documented about which publications they draw on. We conducted an exploratory study of...

Pressfront Research · 0 citations
#small language model Open access Sep 2026

Continued-Fraction Statistics Cannot Tell Known Transcendentals from Unknown Ones or from a Cubic Irrational ── the geometric mean of partial quotients, the growth of denominators and the share of ones all fall within the scatter of random numbers for eight named numbers, and only periodic quadratic numbers and the patterned e stand out ── the separator is whether one speaks of almost all numbers in measure or of this number by name ── [Paper 1021]

Whether π + e, πe or γ is transcendental is not known. On the other hand, it is known that for almost all real numbers the geometric mean of the partial quotients of the continued fraction approaches Khinchin’s constant (Khinchin). This paper expands to 3000 terms the continued fractions of numbers known to be transcen...

Yuuki Yamagishi · 0 citations
#small language model Open access Sep 2026

NHOS Children's Symptoms Checker™ A Client-Side Naive Bayes Pediatric Triage Aid with a 50-Level Triage Severity Score, 3,392-Condition Library, 17-System Coverage, Integrated Interactive Visualization, and a Nine-Module Complete Clinical Upgrade Pack Technical Research White Paper — Architecture, Methodology, Validation Framework, Reproducibility Specification, and Complete Clinical Upgrade Manifest

The NHOS Children's Symptoms Checker™ (NHOS-CSC) is a fully client-side pediatric symptom-triage artifact released as informational research software. It is designed to answer a narrow methodological research question: can a compact, fully inspectable, browser-local pediatric symptom-triage tool expose its assumptions...

Inc. NHOS Labs, Adedapo Ogundiran · 0 citations
#small language model Open access Sep 2026

Converting legacy media to text to increase findability of cultural records

Many recordings made in the past have little metadata and so are difficult to find by normal catalog searches. We have been exploring the use of language models for automated speech recognition (ASR) with very small training sets, in one case (Bislama) 29 hours of transcribed audio, and, in the other (Nafsan) 10 hours....

Aso Mahmudi, Nick Thieberger, Raphaël Merx et al. · 0 citations
#small language model Open access Sep 2026

A discrete relational model built from local difference, rotation, and closure — k-Flip Theory (A–E)

Dear Researcher, I am sharing a working research archive titled k-Flip Theory, now available on Zenodo as a five-part set (A–E). The project began from a deliberately simple question: If two physical contributions cancel to zero, what exactly has disappeared? The working premise is that zero net value need not erase th...

t sato · 0 citations
#small language model Open access Sep 2026

Reversing an Iron Rod's Magnetization Spins It at a Rate Independent of Length, Halved When g Is 2 Instead of 1 ── the angular speed is 8 Mₛ mₑ/(g e ρ r²), inversely proportional to the square of the radius, and on a fibre of period 10 seconds one reversal swings the rod 0.900766 degrees for g equal to 1 and 0.450383 degrees for 2 ── the separator is whether the angular momentum is carried by orbital motion or by spin ── [Paper 1012]

Anything with a magnetic moment also carries angular momentum, so reversing a magnetization sets the body spinning with the difference (Einstein and de Haas 1915). This paper counts, for an iron cylinder, the angular speed gained in a reversal, the swing on a torsion fibre, and how small the rotational energy is. No ne...

Yuuki Yamagishi · 0 citations
#small language model Open access Sep 2026

Reading User Distress From the Inside: Do a Language Model's Hidden States Track a Person's Distress Better Than the Model's Own Reply Does?

When a person tells an AI assistant about something painful, two things happeninside the model that we can measure separately. First, the model builds aninternal reading of how distressed the person is; this reading can be recovered fromits hidden states with a simple trained readout. Second, the model produces a reply...

Anant Pareek · 0 citations
#small language model Open access Sep 2026

Counting a Ball by Lattice Points, the Error Comes from the Skin in Low Dimensions and from One Shell in High Ones ── lining up the Gauss circle problem by dimension, the unsolved dimensions 2 and 3 are those where the accumulated fluctuation of the skin is not beaten by the jump of a single shell ── the separator is whether the error is an accumulation of jumps or a single jump ── [Paper 1015]

Counting the lattice points in a ball of radius r departs from the volume V times r to the power d (the content). Asking how large this departure is in two dimensions is the Gauss circle problem, and it is still unsolved in two and three dimensions. This paper measures the departure in the same way for dimensions d = 2...

Yuuki Yamagishi · 0 citations
#small language model Open access Sep 2026

Whether a Sum of Powers Has Many Solutions Depends on Whether Its Exponents Make a Spherical, Flat or Hyperbolic Triangle ── when the triangle with angles π/a, π/b, π/c has angle sum above π it lies on a sphere and the primitive solutions form families, below π it is hyperbolic and they are finite, and Fermat's n = 2, 3, 4 fall one into each ── the separator is whether the sum of the reciprocal exponents exceeds 1 ── [Paper 1016]

The integer solutions of x to the power a plus y to the power b equal to z to the power c (the generalized Fermat equation) change greatly with the exponents. The Beal conjecture and the Fermat-Catalan conjecture are open questions about parts of this. This paper forms from the exponents a triangle with angles π/a, π/b...

Yuuki Yamagishi · 0 citations
#small language model Open access Sep 2026

Critical Mass Is Set by Skin Balancing Content, Yet a Cube's Extra Volume Does Not Match Its Surface Coefficient ── in a bare one-group diffusion sphere, neutrons leaking through the skin over those gained in the content equal the square of the critical radius over the radius, and a cube's critical-volume factor 1.240490 is smaller than its equal-volume surface coefficient 1.240701 ── the separator is whether the weight of a shape is set by surface area or by the first eigenvalue ── [Paper 1007]

Whether a fission chain reaction keeps going is decided by the balance between neutrons gained in the content and neutrons leaking through the skin. This paper counts that balance in a bare one-group diffusion core (no reflector, no extrapolation distance, lengths measured in the diffusion length L, and the material re...

Yuuki Yamagishi · 0 citations
#small language model Open access Sep 2026

Powder Arc Fusion (PAF): An Arc-Based Powder Bed Fusion System Concept for Low-Cost Metal Additive Manufacturing

Metal additive manufacturing has seen rapid growth, yet access remains limited by the high cost of established processes such as Selective Laser Melting (SLM), where entry-level systems typically require investments exceeding 100,000 USD. This paper introduces Powder Arc Fusion (PAF), a powder bed fusion concept that r...

Lukas Vogl · 0 citations
#small language model Open access Sep 2026

StivorLing: Digital Documentation and Social Media Revitalization of a Critically Endangered Romance Variety

This paper presents StivorLing (https://stivorling.com/en/home-english/), the first comprehensive, community-driven documentation and revitalization project dedicated to the heritage Italo-Romance variety of Štivor, a small village in Bosnia and Herzegovina. Currently, the variety is critically endangered, with only ap...

Marija Runić, Rossella Montibeler · 0 citations

From tech blogs

See all →
Microsoft Research Blog Oct 12, 2026

Simulating student learning for better AI tutoring

StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.