arXiv:2512.20950v1 Announce Type: cross Abstract: This paper presents our system for SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval. In an era where misinformation spreads rapidly, effective fact-checking is increasingly critical. We introduce TriAligner, a novel approach that leverages a dual-encoder architecture with contrastive learning and incorporates both native and English translations across different […]
The Silent Scholar Problem: A Probabilistic Framework for Breaking Epistemic Asymmetry in LLM Agents
arXiv:2512.20884v1 Announce Type: new Abstract: Autonomous agents powered by LLMs and Retrieval-Augmented Generation (RAG) are proficient consumers of digital content but remain unidirectional, a limitation we term epistemic asymmetry. This isolation leads to redundant reasoning and stagnates collective intelligence. Current self-reflection frameworks remain largely heuristic and private, lacking a probabilistic foundation to quantify certainty or […]
Gobernanza y trazabilidad “a prueba de AI Act” para casos de uso legales: un marco t’ecnico-jur’idico, m’etricas forenses y evidencias auditables
arXiv:2510.12830v2 Announce Type: replace-cross Abstract: This paper presents a comprehensive governance framework for AI systems in the legal sector, designed to ensure verifiable compliance with the EU AI Act. The framework integrates a normative mapping of the regulation to technical controls, a forensic architecture for RAG/LLM systems, and an evaluation system with metrics weighted by […]
Clever Hans in Chemistry: Chemist Style Signals Confound Activity Prediction on Public Benchmarks
arXiv:2512.20924v1 Announce Type: new Abstract: Can machine learning models identify which chemist made a molecule from structure alone? If so, models trained on literature data may exploit chemist intent rather than learning causal structure-activity relationships. We test this by linking CHEMBL assays to publication authors and training a 1,815-class classifier to predict authors from molecular […]
Guardrailed Elasticity Pricing: A Churn-Aware Forecasting Playbook for Subscription Strategy
arXiv:2512.20932v1 Announce Type: cross Abstract: This paper presents a marketing analytics framework that operationalizes subscription pricing as a dynamic, guardrailed decision system, uniting multivariate demand forecasting, segment-level price elasticity, and churn propensity to optimize revenue, margin, and retention. The approach blends seasonal time-series models with tree-based learners, runs Monte Carlo scenario tests to map risk […]
FinAgent: An Agentic AI Framework Integrating Personal Finance and Nutrition Planning
arXiv:2512.20991v1 Announce Type: new Abstract: The issue of limited household budgets and nutritional demands continues to be a challenge especially in the middle-income environment where food prices fluctuate. This paper introduces a price aware agentic AI system, which combines personal finance management with diet optimization. With household income and fixed expenditures, medical and well-being status, […]
Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
arXiv:2510.00915v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to $,1$, but imperfect verifiers inevitably introduce emphfalse negatives (rejecting correct answers) and emphfalse positives (accepting incorrect ones). We formalize verifier unreliability as a stochastic reward channel with […]
Multiple-Timescale Solutions to the Susceptible-Infected-Recovered (SIR) Epidemic Model Equations in the Case of High Basic Reproduction Number
arXiv:2512.20663v1 Announce Type: new Abstract: A class of multiple-timescale asymptotic solutions to the equations of the susceptible-infected-recovered (SIR) model is presented for the case of high basic reproduction number, with the inverse of the latter employed as the expansion parameter. High values of the basic reproduction number, a coefficient defined as the ratio of the […]
RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks
arXiv:2512.20920v1 Announce Type: cross Abstract: Full parameter fine tuning is a key technique for adapting large language models (LLMs) to downstream tasks, but it incurs substantial memory overhead due to the need to cache extensive intermediate activations for backpropagation. This bottleneck makes full fine tuning of contemporary large scale LLMs challenging in practice. Existing distributed […]
Bridging the AI Trustworthiness Gap between Functions and Norms
arXiv:2512.20671v1 Announce Type: new Abstract: Trustworthy Artificial Intelligence (TAI) is gaining traction due to regulations and functional benefits. While Functional TAI (FTAI) focuses on how to implement trustworthy systems, Normative TAI (NTAI) focuses on regulations that need to be enforced. However, gaps between FTAI and NTAI remain, making it difficult to assess trustworthiness of AI […]