--- title: "CLARIESG — paper by Santacroce et al. (2026)" description: "The authors present CLARIESG, a demo system with two layers. 7.0 points. 1 reference. Among them: 0." authors: ["Marta Santacroce", "Michele Luca Contalbo", "Sara Pederzoli", "Riccardo Benassi", "Venturelli Valeria", "Matteo Paganelli", "Francesco Guerra"] year: 2026 venue: "Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)" source: "https://aclanthology.org/2026.eacl-demo.7/" doi: "10.18653/v1/2026.eacl-demo.7" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/santacroce-2026-clariesg-end-end-system-esg/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/santacroce-2026-clariesg-end-end-system-esg/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/) / CLARIESG: An End-to-End System for ESG Analysis over Complex Tables in Corporate Reports # CLARIESG: An End-to-End System for ESG Analysis over Complex Tables in Corporate Reports **Authors:** Marta Santacroce, Michele Luca Contalbo, Sara Pederzoli, Riccardo Benassi, Venturelli Valeria, Matteo Paganelli and Francesco Guerra · **Year:** 2026 · **Venue:** [Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.eacl-demo.7/) · [PDF](https://aclanthology.org/2026.eacl-demo.7.pdf) · [DOI 10.18653/v1/2026.eacl-demo.7](https://doi.org/10.18653/v1/2026.eacl-demo.7) · [OpenAlex](https://openalex.org/W7140114681) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary Corporate sustainability reports are a major source of ESG data, but their tables are irregular, with merged headers, nested indicators and company-specific schemas. Their indicators also use inconsistent units, and many questions require arithmetic across several tables or reports. Existing LLM-based tools rarely address all of these issues together. The authors present CLARIESG, a demo system with two layers. A data preparation layer finds the company and its sector through Wikidata, locates GRI-relevant pages with hybrid retrieval, and extracts tables using an OCR ensemble. An LLM then filters and repairs those tables, and users can correct the results through a human-in-the-loop interface. An analytics layer answers questions with NormPoT, a prompting scheme that filters candidate tables, derives unit-conversion rules and then writes and runs Python code. On the multi-table GRI-QA benchmark, NormPoT clearly beats Chain-of-Thought, and CLARIESG with gpt-5-mini far outperforms ChatGPT 5.1 given the full reports. This makes ESG benchmarking and greenwashing claim checks more accurate and auditable. ## Key points - **Data preparation pipeline:** - Retrieval combines multilingual-e5-large-instruct embeddings with TF-IDF. - Tables are extracted by an ensemble of Unstructured and Tesseract. - An LLM refines tables in two steps: a GRI relevance check, then structure and format correction. - The interface is built with Gradio 5.46.0 and calls the OpenAI API. - **Demo scenarios:** analysts can ask natural-language questions and receive answers with scorecards, or submit claims for verification against evidence in the reports. - **One-table GRI-QA results (normalized EM):** - Plain CoT scores best on average (72.7). - PoT drops 7.0 points and NormPoT drops 7.9. - On the quant subset, however, PoT and NormPoT gain about 13 points. - **Multi-table GRI-QA results:** NormPoT reaches 48.4 average EM, 16.0 points above CoT (32.4). PoT gains 8.8 points. - **Comparison with ChatGPT 5.1 (42.2 EM, first 50 questions per multi-table subset):** - CLARIESG with gpt-4o-mini scores 49.1, but falls to 35.8 when irrelevant "noisy" tables are added. - With gpt-5-mini it reaches 79.1 on clean tables and 77.6 with noisy tables. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [University of Modena and Reggio Emilia](https://md.research.elamur.ai/free/en/universities/university-of-modena-and-reggio-emilia/) — University, Modena, Italy · 3 works · 3 citations 📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [💼 Business, Management and Accounting](https://md.research.elamur.ai/free/en/shelves/business-management-and-accounting/) · 32 works · [💼 Strategy and Management](https://md.research.elamur.ai/free/en/shelves/business-management-and-accounting/strategy-and-management/) · 4 works ## Cite Cite as: Marta Santacroce, Michele Luca Contalbo, Sara Pederzoli, Riccardo Benassi, Venturelli Valeria, Matteo Paganelli and Francesco Guerra. 2026. CLARIESG: An End-to-End System for ESG Analysis over Complex Tables in Corporate Reports. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{santacroce2026clariesg, title = {{CLARIESG: An End-to-End System for ESG Analysis over Complex Tables in Corporate Reports}}, author = {Marta Santacroce, Michele Luca Contalbo, Sara Pederzoli, Riccardo Benassi, Venturelli Valeria, Matteo Paganelli and Francesco Guerra}, booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)}, year = {2026}, doi = {10.18653/v1/2026.eacl-demo.7}, url = {https://doi.org/10.18653/v1/2026.eacl-demo.7} } ``` - [← previous CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents](https://md.research.elamur.ai/free/en/papers/roh-2026-clag-adaptive-memory-organization-agent/) - [next → CLARIN-PT-LDB: An Open LLM Leaderboard for Portuguese to assess Language, Culture and Civility](https://md.research.elamur.ai/free/en/papers/silva-2026-clarin-pt-ldb-open-llm/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/) ## References 1 references, 0 of them with a card of ours. ↗ leads to the work. 1. 2022. Directive (eu) 2022/2464 of the european parliament and of the council of 14 december 2022 on corporate sustainability reporting (csrd). [https://eur-lex.europa.eu/legal-content/](https://eur-lex.europa.eu/legal-content/) EN/TXT/?uri=CELEX:32022L2464. Official Journal of the European Union, L 322, 16 December 2022. \#\# Limitations [↗](https://eur-lex.europa.eu/legal-content/) *Updated 1 November 2026*