Related papers: Proving Test Set Contamination in Black Box Langua…
Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance frameworks increasingly require deleting sensitive data from…
In contrast to their remarkable performance on general knowledge QA, the true abilities of Large Language Models (LLMs) in tasks demanding deep, specialized reasoning, such as in protein biology, have yet to be thoroughly investigated.…
Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. Provably bounding model behavior under such attacks remains…
Can low-cost large language models (LLMs) take over the interpretive coding work that still anchors much of empirical content analysis? This paper introduces ContentBench, a public benchmark suite that helps answer this replacement question…
Large Language Models (LLMs) frequently memorize long sequences verbatim, often with serious legal and privacy implications. Much prior work has studied such verbatim memorization using observational data. To complement such work, we…
The rapid growth in natural language processing (NLP) research has led to numerous new models, outpacing our understanding of how they compare to established ones. One major reason for this difficulty is saturating benchmarks, which may not…
Uncertainty calibration is essential for the safe deployment of large language models (LLMs), particularly when users rely on verbalized confidence estimates. While prior work has focused on classifiers or short-form generation, confidence…
We investigate the predictability of large language model (LLM) capabilities: given records of past experiments using different model families, numbers of parameters, tasks, and numbers of in-context examples, can we accurately predict LLM…
Watermarking has recently emerged as an effective strategy for detecting the outputs of large language models (LLMs). Most existing schemes require white-box access to the model's next-token probability distribution, which is typically not…
In English and other languages, multiple adjectives in noun phrases follow intricate ordering patterns. These patterns have been widely studied in linguistics and provide a useful test case for assessing how language models (LMs) acquire…
We investigate the radioactivity of text generated by large language models (LLM), i.e. whether it is possible to detect that such synthetic input was used to train a subsequent LLM. Current methods like membership inference or active IP…
Recent breakthroughs in diffusion models have exhibited exceptional image-generation capabilities. However, studies show that some outputs are merely replications of training data. Such replications present potential legal challenges for…
The zero-shot cross-lingual ability of models pretrained on multilingual and even monolingual corpora has spurred many hypotheses to explain this intriguing empirical result. However, due to the costs of pretraining, most research uses…
Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…
We propose a system for marking sensitive or copyrighted texts to detect their use in fine-tuning large language models under black-box access with statistical guarantees. Our method builds digital ``marks'' using invisible Unicode…
The rapid advancements of Large Language Models (LLMs) tightly associate with the expansion of the training data size. However, the unchecked ultra-large-scale training sets introduce a series of potential risks like data contamination,…
In this paper, we ask the research question of whether all the datasets in the benchmark are necessary. We approach this by first characterizing the distinguishability of datasets when comparing different systems. Experiments on 9 datasets…
Large language models (LLMs) have demonstrated remarkable progress in code generation, but many existing benchmarks are approaching saturation and offer little guarantee on the trustworthiness of the generated programs. To improve…
Large Language Models (LLMs) are known to produce very high-quality tests and responses to our queries. But how much can we trust this generated text? In this paper, we study the problem of uncertainty quantification in LLMs. We propose a…
Language model benchmarks are pervasive and computationally-efficient proxies for real-world performance. However, many recent works find that benchmarks often fail to predict real utility. Towards bridging this gap, we introduce benchmark…