3 citations · 4 across the 15 of their papers we have counts for
17 papers
How Strong Is the Evidence for the Artificial Hivemind? Reevaluating Evidence for the Open-Ended Homogeneity of Language Models
Rylan Schaeffer, Brando Miranda, Joshua Kazdan +2
Recent research argues that language models exhibit pronounced homogeneity in open-ended generation, framing such behavior as an Artificial Hivemind that poses a long-term threat t…
Internal Data Repetition Destroys Language Models
Jessica Chudnovsky, Joshua Kazdan, Noam Levi +6
Language models are running out of high-quality training data, and even aggressively deduplicated corpora retain some amount of repetition. Earlier controlled studies predated Chin…
Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness
Yegor Denisov-Blanch, Joshua Kazdan, Jessica Chudnovsky +4
Pass@k and other methods of scaling inference compute can improve language model performance in domains with external verifiers, including mathematics and code, where incorrect can…
Scale Dependent Data Duplication
Joshua Kazdan, Noam Levi, Rylan Schaeffer +6
Data duplication during pretraining can degrade generalization and lead to memorization, motivating aggressive deduplication pipelines. However, at web scale, it is unclear what co…
Quantifying the Effect of Test Set Contamination on Generative Evaluations
Rylan Schaeffer, Joshua Kazdan, Baber Abbasi +8
As frontier AI systems are pretrained on web-scale data, test set contamination has become a critical concern for accurately assessing their capabilities. While research has thorou…
Efficient Prediction of Pass@k Scaling in Large Language Models
Joshua Kazdan, Rylan Schaeffer, Youssef Allouah +4
Assessing the capabilities and risks of frontier AI systems is a critical area of research, and recent work has shown that repeated sampling from models can dramatically increase b…
Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed
Isha Gupta, Rylan Schaeffer, Joshua Kazdan +2
The field of adversarial robustness has long established that adversarial examples can successfully transfer between image classifiers and that text jailbreaks can successfully tra…
Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track
Rylan Schaeffer, Joshua Kazdan, Yegor Denisov-Blanch +11
Science progresses by iteratively advancing and correcting humanity's understanding of the world. In machine learning (ML) research, rapid advancements have led to an explosion of…
Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models
Rylan Schaeffer, Joshua Kazdan, Yegor Denisov-Blanch
Sampling from language models impacts the quality and diversity of outputs, affecting both research and real-world applications. Recently, Nguyen et al. 2024's "Turning Up the Heat…
Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF
Syrine Belakaria, Joshua Kazdan, Charles Marx +5
Reinforcement learning from human feedback (RLHF) has become a cornerstone of the training and alignment pipeline for large language models (LLMs). Recent advances, such as direct…
Position: Model Collapse Does Not Mean What You Think
Rylan Schaeffer, Joshua Kazdan, Alvan Caleb Arulandu +1
The proliferation of AI-generated content online has fueled concerns over \emph{model collapse}, a degradation in future generative models' performance when trained on synthetic da…
How Do Large Language Monkeys Get Their Power (Laws)?
Rylan Schaeffer, Joshua Kazdan, John Hughes +7
Recent research across mathematical problem solving, proof assistant programming and multimodal jailbreaking documents a striking finding: when (multimodal) language model tackle a…
No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
Joshua Kazdan, Abhay Puri, Rylan Schaeffer +5
Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to…
KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
Belinda Mo, Kyssen Yu, Joshua Kazdan +6
Recent interest in building foundation models for KGs has highlighted a fundamental challenge: knowledge-graph data is relatively scarce. The best-known KGs are primarily human-lab…
The Utility and Complexity of in- and out-of-Distribution Machine Unlearning
Youssef Allouah, Joshua Kazdan, Rachid Guerraoui +1
Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment. Despit…
Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World
Joshua Kazdan, Rylan Schaeffer, Apratim Dey +4
What happens when generative machine learning models are pretrained on web-scale datasets containing data generated by earlier models? Some prior work warns of "model collapse" as…
CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
Joshua Kazdan, Hao Sun, Jiaqi Han +2
Diffusion models have a tendency to exactly replicate their training data, especially when trained on small datasets. Most prior work has sought to mitigate this problem by imposin…