Papers by Yonatan Oren
A Dataset for Metaphor Detection in Early Medieval Hebrew Poetry (2024.eacl-short)
Copied to clipboard
| Challenge: | a corpus of late antique and medieval Hebrew poetry is rich in metaphors and similes . scholars in the humanities need to distinguish between figurative and literal language . |
| Approach: | They present a corpus of late antique and medieval Hebrew poetry with expert annotations of metaphor . they hope to facilitate further research in this area . |
| Outcome: | The proposed dataset includes a corpus of late antique and medieval Hebrew poetry with expert annotations of metaphor. |
Distributionally Robust Language Modeling (D19-1)
Copied to clipboard
| Challenge: | Language models are generally trained on data spanning a wide range of topics but might be applied to an unknown target distribution. |
| Approach: | They propose a distributionally robust optimization procedure which minimizes the loss of the model over the worst-case mixture of topics with sufficient overlap with the training distribution. |
| Outcome: | The proposed method reduces the loss of the model over the worst-case mixture of topics with sufficient overlap with the training distribution. |
ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogies (2024.naacl-long)
Copied to clipboard
| Challenge: | Analogy-making is a central to human cognition, allowing us to abstract information and understand novel situations in terms of familiar ones. |
| Approach: | They propose a pipeline to generate paragraph-based analogies using large language models and large language distractors. |
| Outcome: | The proposed pipeline outperforms existing models in binary and multiple-choice settings and shows that humans outperformed the best models after a light supervision. |
Improving LLM Attributions with Randomized Path-Integration (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in AI research have impacted numerous application domains, fueling innovation and progress in user modeling and personalization. |
| Approach: | They propose a path-integration method for explaining language models via randomization of the integration path over the attention information in the model. |
| Outcome: | The proposed method outperforms state-of-the-art methods across 4 datasets and 5 evaluation metrics. |
LLM Explainability via Attributive Masking Learning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | In this paper, we introduce Attributive Masking Learning (AML), a method designed for explaining language model predictions by learning input masks. |
| Approach: | They introduce a method for explaining language model predictions by learning input masks and ensuring a significant change in the model's explanation when applying the inverse mask to the input. |
| Outcome: | The proposed method outperforms state-of-the-art explanation methods on multiple benchmarks. |