arXiv:2512.02251v1 Announce Type: new 
Abstract: Climate adaptation strategies are proposed in response to climate change. They are practised in agriculture to sustain food production. These strategies can be found in unstructured data (for example, scientific literature from the Elsevier website) or structured (heterogeneous climate data via government APIs). We present Climate Adaptation question-answering with Improved Readability and Noted Sources (CAIRNS), a framework that enables experts -- farmer advisors -- to obtain credible preliminary answers from complex evidence sources from the web. It enhances readability and citation reliability through a structured ScholarGuide prompt and achieves robust evaluation via a consistency-weighted hybrid evaluator that leverages inter-model agreement with experts. Together, these components enable readable, verifiable, and domain-grounded question-answering without fine-tuning or reinforcement learning. Using a previously reported dataset of expert-curated question-answers, we show that CAIRNS outperforms the baselines on most of the metrics. Our thorough ablation study confirms the results on all metrics. To validate our LLM-based evaluation, we also report an analysis of correlations against human judgment.

تم تقديم إطار CAIRNS لتحسين استراتيجيات التكيف مع المناخ من خلال تزويد مستشاري المزارعين بإجابات أولية موثوقة مستمدة من مصادر معقدة على الويب. تهدف هذه المبادرة إلى تحسين قابلية القراءة وموثوقية الاقتباسات من خلال نهج منظم، مما يسمح بطرح الأسئلة بشكل فعال دون الحاجة إلى ضبط دقيق أو تعلم معزز.

Se ha introducido el marco CAIRNS para mejorar las estrategias de adaptación al clima, proporcionando a los asesores agrícolas respuestas preliminares creíbles extraídas de fuentes complejas en la web. Esta iniciativa busca mejorar la legibilidad y la fiabilidad de las citas a través de un enfoque estructurado, permitiendo un cuestionamiento efectivo sin necesidad de ajuste fino o aprendizaje por refuerzo.

Le cadre CAIRNS a été introduit pour améliorer les stratégies d'adaptation au climat en fournissant aux conseillers agricoles des réponses préliminaires crédibles tirées de sources complexes sur le web. Cette initiative vise à améliorer la lisibilité et la fiabilité des citations grâce à une approche structurée, permettant un questionnement efficace sans nécessiter de réglage fin ou d'apprentissage par renforcement.

The CAIRNS framework has been introduced to enhance climate adaptation strategies by providing farmer advisors with credible preliminary answers sourced from complex evidence on the web. This initiative aims to improve readability and citation reliability through a structured approach, allowing for effective question-answering without the need for fine-tuning or reinforcement learning.

CAIRNS: Balancing Readability and Scientific Accuracy in Climate Adaptation Question Answering

arXiv:2505.07409v2 Announce Type: replace 
Abstract: Democratic societies need reliable information. Misinformation in popular media, such as news articles or videos, threatens to impair civic discourse. Citizens are, unfortunately, not equipped to verify the flood of content consumed daily at increasing rates. This work aims to quantify the scientific accuracy of online media semi-automatically. We investigate the state of the art of climate-related ground truth knowledge representation. By semantifying media content of unknown veracity, their statements can be compared against these ground truth knowledge graphs. We implemented a workflow using LLM-based statement extraction and knowledge graph analysis. Our implementation can streamline content processing towards state-of-the-art knowledge representation and veracity quantification. Developed and evaluated with the help of 27 experts and detailed interviews with 10, the tool evidently provides a beneficial veracity indication. These findings are supported by 43 anonymous participants from a parallel user survey. This initial step, however, is unable to annotate public media at the required granularity and scale. Additionally, the identified state of climate change knowledge graphs is vastly insufficient to support this neurosymbolic fact-checking approach. Further work towards a FAIR (Findable, Accessible, Interoperable, Reusable) ground truth and complementary metrics is required to support civic discourse scientifically.

قدمت دراسة جديدة تدفق عمل شبه آلي لت quantifying دقة المعلومات العلمية في المقالات الإخبارية المتعلقة بتغير المناخ. تستخدم هذه الطريقة نماذج لغوية كبيرة (LLMs) لاستخراج البيانات ومقارنتها مع الرسوم البيانية المعرفية المعتمدة، بهدف تعزيز موثوقية المعلومات في المجتمعات الديمقراطية.

Un nuevo estudio ha presentado un flujo de trabajo semi-automatizado para cuantificar la precisión científica de los artículos de noticias relacionados con el cambio climático. Este método utiliza modelos de lenguaje de gran tamaño (LLMs) para extraer declaraciones y compararlas con gráficos de conocimiento establecidos, con el objetivo de mejorar la fiabilidad de la información en sociedades democráticas.

Une nouvelle étude a introduit un flux de travail semi-automatisé pour quantifier l'exactitude scientifique des articles de presse liés au changement climatique. Cette méthode utilise des modèles de langage de grande taille (LLMs) pour extraire des déclarations et les comparer à des graphes de connaissances établis, visant à améliorer la fiabilité de l'information dans les sociétés démocratiques.

A new study has introduced a semi-automated workflow for quantifying the scientific accuracy of climate change-related news articles. This method utilizes large language models (LLMs) to extract statements and compare them against established knowledge graphs, aiming to enhance the reliability of information in democratic societies.

CAIRNS: Balancing Readability and Scientific Accuracy in Climate Adaptation Question Answering

Was this article worth reading? Share it

LucidQuery AI

Sourcely

EnumAI