English
Related papers

Related papers: How Much Can We Forget about Data Contamination?

200 papers

LLMs produce harmful and undesirable behavior when trained on datasets containing even a small fraction of poisoned data. We demonstrate that GPT models remain vulnerable to fine-tuning on poisoned data, even when safeguarded by moderation…

Cryptography and Security · Computer Science 2025-07-18 Dillon Bowen , Brendan Murphy , Will Cai , David Khachaturov , Adam Gleave , Kellin Pelrine

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…

Computation and Language · Computer Science 2024-04-30 Ruijie Xu , Zengzhi Wang , Run-Ze Fan , Pengfei Liu

Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled…

Computation and Language · Computer Science 2026-03-26 Avni Mittal

Why do larger language models generalize better? To investigate this question, we develop generalization bounds on the pretraining objective of large language models (LLMs) in the compute-optimal regime, as described by the Chinchilla…

Machine Learning · Computer Science 2025-04-22 Marc Finzi , Sanyam Kapoor , Diego Granziol , Anming Gu , Christopher De Sa , J. Zico Kolter , Andrew Gordon Wilson

Large language models (LLMs) are often fine-tuned for use on downstream tasks, though this can degrade capabilities learned during previous training. This phenomenon, often referred to as catastrophic forgetting, has important potential…

Computation and Language · Computer Science 2024-12-30 Megan Ung , Alicia Sun , Samuel J. Bell , Bhaktipriya Radharapu , Levent Sagun , Adina Williams

Recent advances in Large Language Models (LLMs) have exhibited remarkable proficiency across various tasks. Given the potent applications of LLMs in numerous fields, there has been a surge in LLM development. In developing LLMs, a common…

Computation and Language · Computer Science 2024-01-09 Chen-An Li , Hung-Yi Lee

Benchmark scores for Large Language Models (LLMs) can be inflated by memorization of test items or near duplicates. We present a simple, protocol that probes generalization by re-evaluating models on paraphrased versions of benchmark…

Computation and Language · Computer Science 2025-10-13 Juan Miguel Navarro Carranza

Hampering the interpretation of benchmark scores, evaluation data contamination has become a growing concern in the evaluation of LLMs, and an active area of research studies its effects. While evaluation data contamination is easily…

Computation and Language · Computer Science 2024-11-07 Aaditya K. Singh , Muhammed Yusuf Kocyigit , Andrew Poulton , David Esiobu , Maria Lomeli , Gergely Szilvasy , Dieuwke Hupkes

Data contamination, i.e., the presence of test data from downstream tasks in the training data of large language models (LLMs), is a potential major issue in measuring LLMs' real effectiveness on other tasks. We propose a straightforward…

Computation and Language · Computer Science 2024-02-23 Shahriar Golchin , Mihai Surdeanu

Scaling laws are powerful tools to predict the performance of large language models. However, current scaling laws fall short of accounting for inference costs. In this work, we first show that model architecture affects inference latency,…

Machine Learning · Computer Science 2025-06-10 Song Bian , Minghao Yan , Shivaram Venkataraman

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,…

Cryptography and Security · Computer Science 2026-03-03 Han Wang , Haoyu Li , Brian Ko , Huan Zhang

The pursuit of leaderboard rankings in Large Language Models (LLMs) has created a fundamental paradox: models excel at standardized tests while failing to demonstrate genuine language understanding and adaptability. Our systematic analysis…

Computation and Language · Computer Science 2024-12-06 Sourav Banerjee , Ayushi Agarwal , Eishkaran Singh

Large language models~(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity. To assess the model performance, a typical approach is to construct evaluation benchmarks for…

Computation and Language · Computer Science 2023-11-06 Kun Zhou , Yutao Zhu , Zhipeng Chen , Wentong Chen , Wayne Xin Zhao , Xu Chen , Yankai Lin , Ji-Rong Wen , Jiawei Han

Large language models (LLMs) have shown remarkable performance on a variety of NLP tasks, and are being rapidly adopted in a wide range of use cases. It is therefore of vital importance to holistically evaluate the factuality of their…

Computation and Language · Computer Science 2024-04-26 Jiaqing Yuan , Lin Pan , Chung-Wei Hang , Jiang Guo , Jiarong Jiang , Bonan Min , Patrick Ng , Zhiguo Wang

Large Language Models (LLMs) demonstrate remarkable capabilities, but their training on massive corpora poses significant risks from memorized sensitive information. To mitigate these issues and align with legal standards, unlearning has…

Computation and Language · Computer Science 2025-11-18 Ruichen Qiu , Jiajun Tan , Jiayue Pu , Honglin Wang , Xiao-Shan Gao , Fei Sun

A widespread strategy to obtain a language model that performs well on a target domain is to finetune a pretrained model to perform unsupervised next-token prediction on data from that target domain. Finetuning presents two challenges: (i)…

Machine Learning · Computer Science 2025-05-28 Louis Bethune , David Grangier , Dan Busbridge , Eleonora Gualdoni , Marco Cuturi , Pierre Ablin

In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread adoption of Pretrained Language Models (PLMs) and Large Language Models (LLMs) has raised concerns…

Software Engineering · Computer Science 2026-02-09 Zhen Yang , Hongyi Lin , Yifan He , Junqi Wang , Zeyu Sun , Shuo Liu , Jie Xu , Pengpeng Wang , Zhongxing Yu , Qingyuan Liang

While existing benchmarks demonstrate the near-perfect performance of large language models (LLMs) on various tasks, this apparent saturation often obscures the need for rigorous evaluation of their reliability. In real-world deployment,…

Machine Learning · Computer Science 2026-05-13 Eungyeup Kim , Chenchen Gu , Vashisth Tiwari , J. Zico Kolter

Publishing a large language model (LLM) benchmark on the Internet risks contaminating future LLMs: the benchmark may be unintentionally (or intentionally) used to train or select a model. A common mitigation is to keep the benchmark private…

Machine Learning · Computer Science 2025-10-07 Takashi Ishida , Thanawat Lodkaew , Ikko Yamane

Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…

Computation and Language · Computer Science 2026-05-19 Xiaoyu Xu , Xiang Yue , Yang Liu , Qingqing Ye , Huadi Zheng , Peizhao Hu , Minxin Du , Haibo Hu