small language model

Application of Retrieval-Augmented Generation Large Language Models in Stomatology: A Scoping Review

Large language models (LLMs) have been gradually applied to tasks such as specialized question answering, educational assistance, clinical decision support, and knowledge integration in stomatology. However, general-purpose LLMs still suffer from critical limitations, including outdated knowledge, hallucinatory generat...

FORTE: Adaptive Scoring and Exact Keyframe Selection for Long-Video Question Answering

This work introduces FORTE, a training-free framework that addresses the challenge of adaptive relevance scoring and global keyframe optimization through two stages: adaptive relevance scoring and global keyframe optimization.

Skeleton-and-Strategy Prompting: Training-Free Negation Understanding for Vision-Language Models

SSP first abstracts the underlying question structure into a skeleton, retrieves a small set of same-skeleton questions from a lightweight question pool, then prompts the VLM to analyze their shared negation pattern and synthesize a single-sentence answering strategy.

In silico designing of small molecules for targeting RNA: current landscape and future directions

Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models

Keyword-matching benchmarks can credit small models for tool use they never perform. We document such a false positive in a matched-architecture pair of Spanish security language models and propose a ladder of strict, cheap diagnostics. A 661.6M parameter model (approx. 65% code/technical text; no dedicated SFT) and a...

Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation

Automated ideation systems are often evaluated on the novelty of the ideas they produce, and that judgment is increasingly delegated to large language models. Such judges are typically built ad hoc and validated, if at all, on human-authored papers rather than on the generated ideas they are meant to score. So, how do...

Yo-ByT5: Efficient and High-Fidelity Diacritic Restoration for Yor\`ub\'a

Yor\`ub\'a is a widely spoken tonal language that depends on diacritics to avoid lexical ambiguity. However, it is often written without these diacritics, thereby hindering downstream Natural Language Processing (NLP) tasks. In this paper, we introduce Yo-ByT5, a byte-level Automatic Diacritic Restoration (ADR) model f...

How the Audit Rule Shapes Faithful Factor Explanations in LLMs

Large language models are often asked which input factors influenced their outputs. For structured inputs, such reports can be checked by counterfactual perturbation, but each factor must be queried multiple times to estimate its effect, so verification is usually budget-limited. We study how this limited-budget settin...

What Wins a Vote? Formatting, Length, and Lexical Diversity in the French Compar:IA LLM Arena

LLM arenas turn pairwise human preferences into model rankings. Those preferences may reflect how an answer is presented as well as what it says. We take a stylometric approach to 137,293 decisive French-language votes from the July 2026 Compar:IA release; the primary formatting analysis includes 137,113 battles across...

Towards Robust Numerical Claim Verification

Large language models (LLMs) are widely used for claim verification, yet remain brittle for numerical reasoning: even small changes in value can sharply degrade accuracy. We show that this brittleness persists in frontier LLMs, but can be mitigated through adversarial fine-tuning on numerically perturbed examples. Usin...

PhysicsMate: A Curriculum-Grounded Bengali Benchmark for Secondary Physics QA with Small-Model Adaptation

Bengali secondary education lacks curriculum-grounded benchmarks for STEM question-solving, and general-purpose language models struggle with the precise terminology, unit conventions, and derivations that physics problems demand. We introduce PhysicsMate, a benchmark of 1834 question-answer pairs built from the Nation...

Reason in Style: Discovering and Controlling Style in Language Models

Language models learn content and style jointly, making stylistic variation in their outputs difficult to identify and control. We study whether recurring styles in model responses can be discovered without supervision and explicitly controlled. We design an algorithm that learns to separate representations of content...