osunlp/AttributionBench

Tasks

• text-classification

Citation text from the card

- Github repository: <a href="https://github.com/OSU-NLP-Group/AttributionBench/">[Github]</a>
- Paper: <a href="https://arxiv.org/abs/2402.15089">AttributionBench: How Hard is Automatic Attribution Evaluation?</a>
- Point of Contact: <a href="mailto:[email protected]">Yifei Li</a>

<section class="section" id="BibTeX">
    <div class="container is-max-desktop content">
      <h2 class="title">Reference</h2>
      Please kindly cite our paper if you use our code, data, or results:
      <pre><code>@misc{li2024attributionbench,
            title={AttributionBench: How Hard is Automatic Attribution Evaluation?}, 
            author={Yifei Li and Xiang Yue and Zeyi Liao and Huan Sun},
            year={2024},
            eprint={2402.15089},
            archivePrefix={arXiv},
            primaryClass={cs.CL}
      }
      </code></pre>
      If used, please also cite the original datasets accordingly:
      <pre><code>@misc{malaviya2023expertqa,
        title={ExpertQA: Expert-Curated Questions and Attributed Answers}, 
        author={Chaitanya Malaviya and Subin Lee and Sihao Chen and Elizabeth Sieber and Mark Yatskar and Dan Roth},
        year={2023},
        eprint={2309.07852},
        archivePrefix={arXiv},
        primaryClass={cs.CL}
      }
      </code></pre>
      <pre><code>@inproceedings{liu-etal-2023-evaluating,
          title = "Evaluating Verifiability in Generative Search Engines",
          author = "Liu, Nelson  and
            Zhang, Tianyi  and
            

All datasets marked Permissive or share-alike | JSON