Yulia Tsvetkov

Affiliations

Carnegie Mellon University

papers

1,277

total citations

papers (14)

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

ICLR 2024arXiv

581

citations

Can Language Models Solve Graph Problems in Natural Language?

NEURIPS 2023arXiv

304

citations

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

ICLR 2024arXiv

166

citations

Controlled Text Generation as Continuous Optimization with Multiple Constraints

NEURIPS 2021arXiv

citations

Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models

ICLR 2024arXiv

citations

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

ICML 2025arXiv

citations

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

NEURIPS 2025arXiv

citations

Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection

COLM 2025arXiv

citations

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

NEURIPS 2025arXiv

citations

Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions

ICLR 2024arXiv

citations

Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?

NEURIPS 2025arXiv

citations

Yulia Tsvetkov

Affiliations

papers (14)

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Can Language Models Solve Graph Problems in Natural Language?

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

Controlled Text Generation as Continuous Optimization with Multiple Constraints

Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions

PrefPalette: Personalized Preference Modeling with Latent Attributes

Sparta Alignment: Collectively Aligning Multiple Language Models through Combat

Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only

Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?

papers (14)

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Can Language Models Solve Graph Problems in Natural Language?

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

Controlled Text Generation as Continuous Optimization with Multiple Constraints

Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions

PrefPalette: Personalized Preference Modeling with Latent Attributes

Sparta Alignment: Collectively Aligning Multiple Language Models through Combat

Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only

Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?