Fang, Haishuo ; Zhu, Xiaodan ; Gurevych, Iryna (2024)
DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs.
62nd Annual Meeting of the Association for Computational Linguistics. Bangkok, Thailand (12.08.2024 -16.08.2024)
doi: 10.18653/v1/2024.findings-acl.203
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Answering Questions over Knowledge Graphs (KGQA) is key to well-functioning autonomous language agents in various real-life applications. To improve the neural-symbolic reasoning capabilities of language agents powered by Large Language Models (LLMs) in KGQA, we propose the Decomposition-Alignment-Reasoning Agent (DARA) framework. DARA effectively parses questions into formal queries through a dual mechanism: high-level iterative task decomposition and low-level task grounding. Importantly, DARA can be efficiently trained with a small number of high-quality reasoning trajectories. Our experimental results demonstrate that DARA fine-tuned on LLMs (e.g. Llama-2-7B, Mistral) outperforms both in-context learning-based agents with GPT-4 and alternative fine-tuned agents, across different benchmarks, making such models more accessible for real-life applications. We also show that DARA attains performance comparable to state-of-the-art enumerating-and-ranking-based methods for KGQA.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Fang, Haishuo ; Zhu, Xiaodan ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs |
| Sprache: | Englisch |
| Publikationsjahr: | 17 August 2024 |
| Verlag: | ACL |
| Buchtitel: | Findings of the Association for Computational Linguistics ACL 2024 |
| Veranstaltungstitel: | 62nd Annual Meeting of the Association for Computational Linguistics |
| Veranstaltungsort: | Bangkok, Thailand |
| Veranstaltungsdatum: | 12.08.2024 -16.08.2024 |
| DOI: | 10.18653/v1/2024.findings-acl.203 |
| URL / URN: | https://aclanthology.org/2024.findings-acl.203/ |
| Kurzbeschreibung (Abstract): | Answering Questions over Knowledge Graphs (KGQA) is key to well-functioning autonomous language agents in various real-life applications. To improve the neural-symbolic reasoning capabilities of language agents powered by Large Language Models (LLMs) in KGQA, we propose the Decomposition-Alignment-Reasoning Agent (DARA) framework. DARA effectively parses questions into formal queries through a dual mechanism: high-level iterative task decomposition and low-level task grounding. Importantly, DARA can be efficiently trained with a small number of high-quality reasoning trajectories. Our experimental results demonstrate that DARA fine-tuned on LLMs (e.g. Llama-2-7B, Mistral) outperforms both in-context learning-based agents with GPT-4 and alternative fine-tuned agents, across different benchmarks, making such models more accessible for real-life applications. We also show that DARA attains performance comparable to state-of-the-art enumerating-and-ranking-based methods for KGQA. |
| Freie Schlagworte: | UKP_p_eliza |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 27 Aug 2024 13:16 |
| Letzte Änderung: | 03 Dez 2024 13:56 |
| PPN: | 524362831 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum