Itay Itzhak


2024

pdf
Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias
Itay Itzhak | Gabriel Stanovsky | Nir Rosenfeld | Yonatan Belinkov
Transactions of the Association for Computational Linguistics, Volume 12

Recent studies show that instruction tuning (IT) and reinforcement learning from human feedback (RLHF) improve the abilities of large language models (LMs) dramatically. While these tuning methods can help align models with human objectives and generate high-quality text, not much is known about their potential adverse effects. In this work, we investigate the effect of IT and RLHF on decision making and reasoning in LMs, focusing on three cognitive biases—the decoy effect, the certainty effect, and the belief bias—all of which are known to influence human decision-making and reasoning. Our findings highlight the presence of these biases in various models from the GPT-3, Mistral, and T5 families. Notably, we find a stronger presence of biases in models that have undergone instruction tuning, such as Flan-T5, Mistral-Instruct, GPT3.5, and GPT4. Our work constitutes a step toward comprehending cognitive biases in instruction-tuned LMs, which is crucial for the development of more reliable and unbiased language models.1

2022

pdf
Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens
Itay Itzhak | Omer Levy
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Standard pretrained language models operate on sequences of subword tokens without direct access to the characters that compose each token’s string representation. We probe the embedding layer of pretrained language models and show that models learn the internal character composition of whole word and subword tokens to a surprising extent, without ever seeing the characters coupled with the tokens. Our results show that the embedding layers of RoBERTa and GPT2 each hold enough information to accurately spell up to a third of the vocabulary and reach high character ngram overlap across all token types. We further test whether enriching subword models with character information can improve language modeling, and observe that this method has a near-identical learning curve as training without spelling-based enrichment. Overall, our results suggest that language modeling objectives incentivize the model to implicitly learn some notion of spelling, and that explicitly teaching the model how to spell does not appear to enhance its performance on such tasks.