small language model

Judging the Judges: A Controlled Audit of Bias and Instability in LLM-as-Judge Evaluation

Large language models are now routinely asked to grade other large language models, a delegation of judgment that has become the default way organizations track progress on open-ended generation tasks where no single reference answer exists. The convenience of this arrangement is undeniable, but it does not remove the...

Adapting a small language model for plant protection information in Türkiye

GraphThought: A Pilot Study on Graph-Structured Multi-Hop Reasoning with a Single Free-Tier LLM

Chain-of-thought (CoT) prompting elicits intermediate reasoning steps from large language models (LLMs), but treats reasoning as a strictly linear sequence. Many multi-hop questions instead decompose naturally into a small directed acyclic graph (DAG) of sub-tasks, some of which are mutually independent. We implement G...

Flow-Guided Chemical Language Modeling for Linker Design in Reticular Chemistry

Reticular chemistry has enabled the synthesis of tens of thousands of metal–organic frameworks (MOFs), yet the discovery of new materials still relies largely on intuition-driven linker design and iterative experimentation. As a result, researchers explore only a small fraction of the vast chemical space accessible to...

GraphThought: A Pilot Study on Graph-Structured Multi-Hop Reasoning with a Single Free-Tier LLM

Chain-of-thought (CoT) prompting elicits intermediate reasoning steps from large language models (LLMs), but treats reasoning as a strictly linear sequence. Many multi-hop questions instead decompose naturally into a small directed acyclic graph (DAG) of sub-tasks, some of which are mutually independent. We implement G...

Structured PREreview of "Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling"

This Zenodo record is a permanently preserved version of a Structured PREreview. You can view the complete PREreview at https://prereview.org/reviews/22662419. Does the introduction explain the objective of the research presented in the preprint? Yes The introduction explains the objective by setting up a gap and then...

The Elephant and the Ant: A Philosophical Study of Magnitude, Fear, Possibility and Existential Power - Vedanta 2.0 | 99+1 Model and Pancha-Sutra

This paper explores the philosophical mystery hidden within the relationship between the Elephant and the Ant. What appears vast is not necessarily complete, and what appears subtle is not necessarily powerless. Through this simple contrast, the study questions human assumptions about magnitude, power, fear, knowledge...

PENGEMBANGAN MEDIA PEMBELAJARAN REPLIKA TV BOX PADA MATA PELAJARAN BAHASA INGGRIS KELAS III SD

Mastering basic English vocabulary in elementary school is a crucial foundation for building students' communication skills; however, the learning process is often hindered by the lack of interactive concrete media, leading to student passivity. The purpose of this study was to develop a valid and practical Replika Tv...

Low-Resource SLM Models for Elastic Semantic Search

Semantic search over domain-specific corpora requires an effective embedding model and infrastructure. Elasticsearch’s native semantic_text field and ELSER sparse-vector inference require a commercial Enterprise subscription, inaccessible to most academic institutions. This paper documents the licensing barrier and pre...

The Impact of Digital and Artificial Intelligence Technologies on the Improvement of Foreign Language Listening, Speaking, Reading and Writing Skills: A Meta‐Analysis

The results demonstrate that digital and AI technologies can effectively support the development of foreign language listening, speaking, reading and writing skills, and suggest that study design, intervention duration and the way multiple technologies are combined may influence estimates of intervention effectiveness.

MultiRSF: A Deep Learning Approach for Predicting RNA-Small-Molecule Binding Sites Using Surface Characteristics

A multimodal deep learning framework that integrates molecular surface fingerprints, contextual sequence embeddings from a pretrained RNA language model and dot bracket secondary structure encoding to predict ligand binding sites on RNA, which provides an accurate and generalizable tool for nucleotide resolution bindin...

Toward Sustainable Urban Mobility: A Multimodal Large Language Model (MLLM) Framework for Automated Driver Performance Assessment with YOLOv8-Based Scene Detection

An exploratory proof-of-concept framework for automated driver evaluation that combines real-world dashcam footage, YOLOv8-based object detection, and multimodal large language models (MLLMs), specifically Gemini 1.5 Flash is presented.