Related papers: Positional Fragility in LLMs: How Offset Effects R…
Human processing of idioms relies on understanding the contextual sentences in which idioms occur, as well as language-intrinsic features such as frequency and speaker-intrinsic factors like familiarity. While LLMs have shown high…
Adapting language models to new data distributions by simple finetuning is challenging. This is due to the rigidity of their subword tokenizers, which typically remain unchanged during adaptation. This inflexibility often leads to…
Despite their wide adoption, the underlying training and memorization dynamics of very large language models is not well understood. We empirically study exact memorization in causal and masked language modeling, across model sizes and…
Large language models (LLMs) often make factually incorrect responses despite their success in various applications. In this paper, we hypothesize that relying heavily on simple co-occurrence statistics of the pre-training corpora is one of…
In the era of high performing Large Language Models, researchers have widely acknowledged that contextual word representations are one of the key drivers in achieving top performances in downstream tasks. In this work, we investigate the…
Visual Generative AI models have demonstrated remarkable capability in generating high-quality images from user inputs like text prompts. However, because these models have billions of parameters, they risk memorizing certain parts of the…
Transformer-based Large Language Models (LLMs) have revolutionized Natural Language Processing by demonstrating exceptional performance across diverse tasks. This study investigates the impact of the parameter initialization scale on the…
Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model performance remain poorly understood. In this work, we decouple the effects of subword…
Large Language Models (LLMs) have shown greatly enhanced performance in recent years, attributed to increased size and extensive training data. This advancement has led to widespread interest and adoption across industries and the public.…
We study how large language models (LLMs) reason about memorized knowledge through simple binary relations such as equality ($=$), inequality ($<$), and inclusion ($\subset$). Unlike in-context reasoning, the axioms (e.g., $a < b, b < c$)…
Language models often struggle with idiomatic, figurative, or context-sensitive inputs, not because they produce flawed outputs, but because they misinterpret the input from the outset. We propose an input-only method for anticipating such…
Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this…
Large Language Models (LLMs) commonly rely on explicit refusal prefixes for safety, making them vulnerable to prefix injection attacks. We introduce HumorReject, a novel data-driven approach that reimagines LLM safety by decoupling it from…
We present Hubble, a suite of fully open-source large language models (LLMs) for the scientific study of LLM memorization. Hubble models come in standard and perturbed variants: standard models are pretrained on a large English corpus, and…
Language models (LMs), despite their advances, often depend on spurious correlations, undermining their accuracy and generalizability. This study addresses the overlooked impact of subtler, more complex shortcuts that compromise model…
Large Language Models (LLMs) are increasingly applied in various real-world scenarios due to their excellent generalization capabilities and robust generative abilities. However, they exhibit position bias, also known as "lost in the…
Large language models often face a three-way trade-off among detection accuracy, inference latency, and deployment cost when used in real-world safety-sensitive applications. This paper introduces Prefix Probing, a black-box harmful content…
While many have shown how Large Language Models (LLMs) can be applied to a diverse set of tasks, the critical issues of data contamination and memorization are often glossed over. In this work, we address this concern for tabular data.…
The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This…
This study investigates the efficacy of Large Language Models (LLMs) in causal discovery. Using newly available open-source LLMs, OLMo and BLOOM, which provide access to their pre-training corpora, we investigate how LLMs address causal…