Related papers: Proving Test Set Contamination in Black Box Langua…
The leakage of benchmark data into the training data has emerged as a significant challenge for evaluating the capabilities of large language models (LLMs). In this work, we challenge the common assumption that small-scale contamination…
If LLM training data is polluted with benchmark test data, then benchmark performance gives biased estimates of out-of-distribution (OOD) generalization. Typical decontamination filters use n-gram matching which fail to detect semantic…
Here we study the problem of learning labels for large text corpora where each text can be assigned a variable number of labels. The problem might seem trivial when the label dimensionality is small and can be easily solved using a series…
Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data, raising the possibility that these models may have been trained on proprietary datasets or the same benchmarks used for evaluation. This…
Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…
Leaderboards for LRMs have turned evaluation into a competition, incentivizing developers to optimize directly on benchmark suites. A shortcut to achieving higher rankings is to incorporate evaluation benchmarks into the training data,…
Recent claims about the impressive abilities of large language models (LLMs) are often supported by evaluating publicly available benchmarks. Since LLMs train on wide swaths of the internet, this practice raises concerns of data…
Recent advances in Vision-Language Models (VLMs) have achieved state-of-the-art performance on numerous benchmark tasks. However, the use of internet-scale, often proprietary, pretraining corpora raises a critical concern for both…
In recent years, climate change repercussions have increasingly captured public interest. Consequently, corporations are emphasizing their environmental efforts in sustainability reports to bolster their public image. Yet, the absence of…
Data contamination has become prevalent and challenging with the rise of models pretrained on large automatically-crawled corpora. For closed models, the training data becomes a trade secret, and even for open models, it is not trivial to…
Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external…
Amid the expanding use of pre-training data, the phenomenon of benchmark dataset leakage has become increasingly prominent, exacerbated by opaque training processes and the often undisclosed inclusion of supervised data in contemporary…
Large Language Models (LLMs) have revolutionized code generation, achieving exceptional results on various established benchmarking frameworks. However, concerns about data contamination - where benchmark data inadvertently leaks into…
Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…
Language models pre-trained on web-scale corpora demonstrate impressive capabilities on diverse downstream tasks. However, there is increasing concern whether such capabilities might arise from evaluation datasets being included in the…
Large language models pretrained on extensive web corpora demonstrate remarkable performance across a wide range of downstream tasks. However, a growing concern is data contamination, where evaluation datasets may be contained in the…
Large language models show strong performance on knowledge intensive tasks such as fact-checking and question answering, yet they often struggle with numerical reasoning. We present a systematic evaluation of state-of-the-art models for…
Multimodal Large Language Models (MLLMs) show impressive vision-language benchmark performance, yet growing concerns about data contamination (test set exposure during training) risk masking true generalization. This concern extends to…
In this position paper, we argue that the classical evaluation on Natural Language Processing (NLP) tasks using annotated benchmarks is in trouble. The worst kind of data contamination happens when a Large Language Model (LLM) is trained on…
English pretrained language models, which make up the backbone of many modern NLP systems, require huge amounts of unlabeled training data. These models are generally presented as being trained only on English text but have been found to…