no code implementations • 12 Mar 2025 • Sara Rajaee, Kumar Pratik, Gabriele Cesa, Arash Behboodi
The most promising recent methods for AI reasoning require applying variants of reinforcement learning (RL) either on rolled out trajectories from the model, even for the step-wise rewards, or large quantities of human annotated trajectory data.
no code implementations • 20 Jun 2024 • Rochelle Choenni, Sara Rajaee, Christof Monz, Ekaterina Shutova
While multilingual language models (MLMs) have been trained on 100+ languages, they are typically only evaluated across a handful of them due to a lack of available test data in most languages.
no code implementations • 3 Feb 2024 • Sara Rajaee, Christof Monz
Recent advances in training multilingual language models on large datasets seem to have shown promising results in knowledge transfer across languages and achieve high performance on downstream tasks.
no code implementations • 1 Feb 2023 • Mohammad Akbar-Tajari, Sara Rajaee, Mohammad Taher Pilehvar
Parameter-efficient fine-tuning approaches have recently garnered a lot of attention.
1 code implementation • 7 Nov 2022 • Sara Rajaee, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar
It has been shown that NLI models are usually biased with respect to the word-overlap between premise and hypothesis; they take this feature as a primary cue for predicting the entailment label.
1 code implementation • Findings (ACL) 2022 • Houman Mehrafarin, Sara Rajaee, Mohammad Taher Pilehvar
The analysis also reveals that larger training data mainly affects higher layers, and that the extent of this change is a factor of the number of iterations updating the model during fine-tuning rather than the diversity of the training samples.
1 code implementation • Findings (ACL) 2022 • Sara Rajaee, Mohammad Taher Pilehvar
However, we observe no such dimensions in the multilingual BERT.
no code implementations • Findings (EMNLP) 2021 • Sara Rajaee, Mohammad Taher Pilehvar
It is widely accepted that fine-tuning pre-trained language models usually brings about performance improvements in downstream tasks.
1 code implementation • ACL 2021 • Sara Rajaee, Mohammad Taher Pilehvar
Based on this observation, we propose a local cluster-based method to address the degeneration issue in contextual embedding spaces.