Papers by Shachar Don-Yehiya
Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI (2024.naacl-demo)
Copied to clipboard
Elron Bandel, Yotam Perlitz, Elad Venezian, Roni Friedman, Ofir Arviv, Matan Orbach, Shachar Don-Yehiya, Dafna Sheinwald, Ariel Gera, Leshem Choshen, Michal Shmueli-Scheuer, Yoav Katz
| Challenge: | Textual data processing pipelines are tailored to specific datasets, task and model combinations. |
| Approach: | They propose a library for customizable textual data preparation and evaluation tailored to generative language models. |
| Outcome: | Unitxt is a library for customizable textual data preparation and evaluation tailored to generative language models. |
ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning (2023.acl-long)
Copied to clipboard
| Challenge: | Pretraining has been shown to scale well with compute, data size and data diversity. |
| Approach: | They propose a method that provides benefits of multitask learning but leverages distributed computation . they propose 'coldfusion' can create synergistic loop where finetuned models can be "recycled" |
| Outcome: | The proposed method outperforms RoBERTa and previous multitask models on 35 datasets. |
Mediocrity is the key for LLM as a Judge Anchor Selection (2026.acl-long)
Copied to clipboard
| Challenge: | a poor selection of an anchor can dramatically reduce correlation with human rankings . traditional reference-based metrics are often ill-suited for open-ended generation . |
| Approach: | They evaluate 22 different anchors on a Arena-Hard-v2.0 dataset and quantify the effect size of anchor selection. |
| Outcome: | The proposed model is better or worse than all other models, but it is rarely indicative of the relative ranking of the models. |
Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney (2023.emnlp-main)
Copied to clipboard
| Challenge: | Generating images with Text-to-Image models often requires multiple trials, where human users iteratively update their prompt based on feedback, namely the output image. |
| Approach: | They compile a dataset of iterative interactions of human users with Midjourney and analyze the dynamics of the user prompts along these iterations. |
| Outcome: | The proposed model produces better images for a specific language style than other models. |
Where to start? Analyzing the potential value of intermediate models (2023.emnlp-main)
Copied to clipboard
| Challenge: | a finetuned model may be better base models than the vanilla pretrained model . this scheme, often referred to as intertraining, is the focus of the present work . |
| Approach: | They propose a scheme to analyze the potential intertraining gain independently for the target dataset and for a base model being considered as a starting point. |
| Outcome: | The proposed model is strong even if training data was not aligned with target dataset. |
The ShareLM Collection and Plugin: Contributing Human-Model Chats for the Benefit of the Community (2025.acl-demo)
Copied to clipboard
| Challenge: | Using human-model conversations is a valuable resource for model development and research, but the open source and research community lags behind. |
| Approach: | They propose a unified set of human conversations with large language models and a plugin for voluntarily contributing user-model conversations. |
| Outcome: | The ShareLM collection and its plugin allow users to share conversations from most platforms. |
PreQuEL: Quality Estimation of Machine Translation Outputs in Advance (2022.emnlp-main)
Copied to clipboard
| Challenge: | A PreQuEL system predicts how well a given sentence will be translated without recourse to the actual translation. |
| Approach: | They propose a task that uses a model to predict how well a given sentence will be translated . they show that the model is sensitive to syntactic and semantic distinctions . |
| Outcome: | The proposed model improves on the Quality-Estimation task and on challenge sets and languages. |