This study presents the first application of a Retrieval Augmented Generation (RAG) model for Nepali legal question answering, addressing data scarcity in low-resource languages. Using BM25 on chunked documents, the RAG pipeline achieved high precision and truthfulness, demonstrating its effectiveness in the Nepali legal domain.
Este conteúdo apresenta CGD-PD, uma camada leve para modelos de linguagem grandes (LLMs) que melhora a resposta a perguntas lógicas de três vias (Verdadeiro/Falso/Desconhecido). Ele aborda falhas recorrentes como inconsistência de negação e previsões 'Desconhecido' epistêmicas, utilizando decisões consistentes e desambiguação baseada em prova para maior precisão.
GRISP is a novel SPARQL-based question-answering method over knowledge graphs, leveraging a fine-tuned small language model (SLM). It generates SPARQL query skeletons from natural language questions and iteratively refines them by selecting knowledge graph items, achieving state-of-the-art results on Wikidata and Freebase benchmarks.
This paper introduces a synthetic contrastive reasoning-trace dataset for multi-table question answering (MMQA), addressing the lack of reasoning supervision in existing resources. Open-weight LLMs fine-tuned with Contrastive Preference Optimization (CPO) using this dataset achieved significant performance improvements, highlighting the benefits of heterogeneous trace generators.
This research paper argues that the bottleneck in large language models' temporal reasoning is not logical deduction but rather unstructured text-to-event representation. It introduces a neuro-symbolic question-answering framework utilizing a Probabilistic Inconsistency Signal (PIS) to decouple semantic extraction from symbolic reasoning, improving performance.
HypEHR is a compact Lorentzian model utilizing hyperbolic geometry to address Electronic Health Record (EHR) question answering, overcoming cost and hierarchical structure challenges of LLM-based methods. It is pretrained for next-visit diagnosis prediction and alignment with medical ontologies, achieving LLM-comparable performance with significantly fewer parameters.
GQA is a new dataset designed to challenge and evaluate AI systems in visual reasoning and compositional question answering. It aims to advance scene understanding and multimodal interaction in real-world scenarios.
This paper addresses the challenges of automated PDF processing for AI, particularly with RAG systems, by proposing an empirical study. It evaluates various PDF parsers and chunking strategies for Question Answering in the financial domain, introducing a new benchmark called TableQuest.
This paper introduces FinAgent-RAG, an agentic RAG framework for financial document question answering, focusing on complex numerical reasoning. It orchestrates iterative retrieval-reasoning loops with self-verification, incorporating a Contrastive Financial Retriever and a Program-of-Thought module for precise arithmetic.