small language model

PREreview of "What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track"

This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/22775771. Summary The authors tackle a real obstacle in interpretability: you can't compare SAE features across training checkpoints, because separately trained dictionaries assign...

AMORE: Adaptive Multi-objective Reward Engineering for Socratic Math Tutoring with Small Language Models

A cross-sectional evaluation of large language model chatbot interfaces for patient-facing herpes zoster information: safety, information quality, and readability

In this standardised benchmark, LLM chatbot interfaces provided generally favourable accuracy and information-quality scores but showed clinically relevant safety limitations, sparse source attribution and disclosure, and readability challenges.

The effects of delayed auditory feedback depend on both the rhythm and content of the feedback signal

Purpose Delayed auditory feedback (DAF) has long been known to disrupt fluent speech, yet the underlying mechanisms remain a matter of debate. Some have hypothesized that interference occurs because of asynchronous sensory and motor rhythms, independent of the specific content of auditory inputs. The goal of this study...

Auditing sex/gender disparities in emergency triage with LLM-based paired comparisons

We present a domain-agnostic paired-comparison approach that uses Large Language Models (LLMs) to quantify sex/gender-related asymmetries in documented clinical decision-making. The method trains an LLM to emulate observed decisions, then evaluates sex-swapped pairs in which only sex is flipped, holding documented clin...

Open or Frontier? A Cost- and Energy-Aware Benchmark of Large Language Models for Software Vulnerability Detection

Efficiency is the robust finding: open-weight models occupy the quality-efficiency Pareto frontier in every configuration tested, and no frontier model is Pareto-optimal; no frontier model is Pareto-optimal.

Genolator enables protein function interpretation using a multimodal large language model fusing genomic and structural interpretation with natural language interaction

Genolator is presented, a multimodal large language model that integrates embeddings from DNA sequences, amino acid sequences, and protein structures with natural language queries and represents a step towards bridging genomic code and human language through the integration of a multimodal LLM.

Qualification by Calibration: A Readable Benchmark for Admitting Language Models to Human-Computation Tasks

Evaluating a diverse panel of contemporary models under three administration protocols, it is shown that a naive harness, with a fixed token budget and an unaudited parser, manufactures failing workers out of competent ones, misreading a model that answers essentially every item correctly as badly inaccurate, answer-bi...

Symbolic Separation: Grounding Deep Agents in Knowledge Graphs for Trustworthy Operational Data Analytics

This work proposes symbolic separation: a deep agent reasons freely but may act on data only through an ontology-constrained Virtual Knowledge Graph with deterministic pre-execution validation, like a tool API's interface contract, but which turns a complex question into one validated graph traversal instead of LLM-inf...

BrainFocus: EEG-Guided ROI Selection for Efficient Vision-Language Models

BrainFocus is proposed, a reliable EEG-guided efficient VLM framework for VQA that improves VQA accuracy and demonstrates that EEG can guide efficient VLM inference even when its semantic decoding is imperfect.

TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models

TecoPrompt, a closed-loop robust prompt-learning framework that revisits optimal transport pseudo-labeling from a temporal perspective, employs an entropic OT plan in the CLIP semantic space to obtain globally consistent label candidates.

FirmCORe: A Benchmark for Structured Reasoning about Inter-Firm Collaboration Opportunities

Results indicate that current LLMs are substantially more reliable at detecting broad collaboration opportunities than at identifying their specific types and role directions.