Yuval Reif

Guy Kaplan, Zorik Gekhman, Zhen Zhu et al.

Large language models are prone to hallucinating factually incorrect statements. A key source of these errors is exposure to new factual information through supervised fine-tuning (SFT), which can increase hallucinations w.r.t. knowledge acquired during pre-training. In this work, we explore whether SFT-induced hallucinations can be mitigated using established tools from the continual learning literature, since they arise as a by-product of knowledge degradation during training. We propose a self-distillation-based SFT method that facilitates effective factual learning while minimizing hallucinations w.r.t. pre-existing knowledge by regularizing output-distribution drift. We also show that, in settings where new knowledge acquisition is unnecessary, suppressing factual plasticity by freezing parameter groups, can preserve task performance while reducing hallucinations. Lastly, we investigate the mechanism behind SFT-induced hallucinations through three hypotheses: capacity limitations, behavior cloning, and localized interference. Our experiments show that a main driver is interference among overlapping semantic representations, and that self-distillation succeeds by mitigating this interference.

Chen Shani, Yuval Reif, Nathan Roll et al.

Multilingual language models (LMs) promise broader NLP access, yet current systems deliver uneven performance across the world's languages. This survey examines why these gaps persist and whether they reflect intrinsic linguistic difficulty or modeling artifacts. We organize the literature around two questions: do linguistic disparities arise from representation and allocation choices (e.g., tokenization, encoding, data exposure, parameter sharing) rather than inherent complexity; and which design choices mitigate inequities across typologically diverse languages. We review linguistic features, such as orthography, morphology, lexical diversity, syntax, information density, and typological distance, linking each to concrete modeling mechanisms. Gaps often shrink when segmentation, encoding, and data exposure are normalized, suggesting much apparent difficulty stems from current modeling choices. We synthesize these insights into design recommendations for tokenization, sampling, architectures, and evaluation to support more balanced multilingual LMs.

Yuval Reif, Roy Schwartz

Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an undesirable preference toward predicting certain answers over others. Still, detecting and measuring this bias reliably and at scale has remained relatively unexplored. In this study, we evaluate different approaches to quantifying label bias in a model's predictions, conducting a comprehensive investigation across 279 classification tasks and ten LLMs. Our investigation reveals substantial label bias in models both before and after debiasing attempts, as well as highlights the importance of outcomes-based evaluation metrics, which were not previously used in this regard. We further propose a novel label bias calibration method tailored for few-shot prompting, which outperforms recent calibration approaches for both improving performance and mitigating label bias. Our results emphasize that label bias in the predictions of LLMs remains a barrier to their reliability.

Guy Kaplan, Michael Toker, Yuval Reif et al.

Text-to-image (T2I) models generate images by encoding text prompts into token representations, which then guide the diffusion process. While prior work has largely focused on improving alignment by refining the diffusion process, we focus on the textual encoding stage. Specifically, we investigate how semantic information is distributed across token representations within and between lexical items (i.e., words or expressions conveying a single concept) in the prompt. We analyze information flow at two levels: (1) in-item representation-whether individual tokens represent their lexical item, and (2) cross-item interaction-whether information flows across the tokens of different lexical items. We use patching techniques to uncover surprising encoding patterns. We find information is usually concentrated in only one or two of the item's tokens-For example, in the item "San Francisco's Golden Gate Bridge", the token "Gate" sufficiently captures the entire expression while the other tokens could effectively be discarded. Lexical items also tend to remain isolated; for instance, the token "dog" encodes no visual information about "green" in the prompt "a green dog". However, in some cases, items do influence each other's representation, often leading to misinterpretations-e.g., in the prompt "a pool by a table", the token pool represents a pool table after contextualization. Our findings highlight the critical role of token-level encoding in image generation, suggesting that misalignment issues may originate already during the textual encoding.

Yuval Reif, Guy Kaplan, Roy Schwartz

Large language models (LLMs) were shown to encode word form variations, such as "walk"->"walked", as linear directions in embedding space. However, standard tokenization algorithms treat these variations as distinct tokens -- filling the size-capped vocabulary with surface form variants (e.g., "walk", "walking", "Walk"), at the expense of less frequent words and multilingual coverage. We show that many of these variations can be captured by transformation vectors -- additive offsets that yield the appropriate word's representation when applied to the base form word embedding -- in both the input and output spaces. Building on this, we propose a compact reshaping of the vocabulary: rather than assigning unique tokens to each surface form, we compose them from shared base form and transformation vectors (e.g., "walked" = "walk" + past tense). We apply our approach to multiple LLMs and across five languages, removing up to 10% of vocabulary entries -- thereby freeing space to allocate new, more diverse tokens. Importantly, we do so while also expanding vocabulary coverage to out-of-vocabulary words, with minimal impact on downstream performance, and without modifying model weights. Our findings motivate a foundational rethinking of vocabulary design, moving from string enumeration to a compositional vocabulary that leverages the underlying structure of language.

Yuval Reif, Roy Schwartz

NLP models often rely on superficial cues known as dataset biases to achieve impressive performance, and can fail on examples where these biases do not hold. Recent work sought to develop robust, unbiased models by filtering biased examples from training sets. In this work, we argue that such filtering can obscure the true capabilities of models to overcome biases, which might never be removed in full from the dataset. We suggest that in order to drive the development of models robust to subtle biases, dataset biases should be amplified in the training set. We introduce an evaluation framework defined by a bias-amplified training set and an anti-biased test set, both automatically extracted from existing datasets. Experiments across three notions of bias, four datasets and two models show that our framework is substantially more challenging for models than the original data splits, and even more challenging than hand-crafted challenge sets. Our evaluation framework can use any existing dataset, even those considered obsolete, to test model robustness. We hope our work will guide the development of robust models that do not rely on superficial biases and correlations. To this end, we publicly release our code and data.