Benjamin Van Durme

papers

806

total citations

papers (20)

Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation

ICML 2024arXiv

414

citations

Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning

CVPR 2023arXiv

105

citations

Rank1: Test-Time Compute for Reranking in Information Retrieval

COLM 2025arXiv

citations

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

ICLR 2025arXiv

citations

Data Portraits: Recording Foundation Model Training Data

NEURIPS 2023arXiv

citations

Zero and Few-shot Semantic Parsing with Ambiguous Inputs

ICLR 2024arXiv

citations

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements

ICLR 2025arXiv

citations

Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images

ICCV 2021arXiv

citations

BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing

NEURIPS 2023arXiv

citations

Ambiguous Images With Human Judgments for Robust Visual Event Classification

NEURIPS 2022arXiv

citations

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

ICLR 2025arXiv

citations

Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval

CVPR 2025arXiv

citations

MultiVENT: Multilingual Videos of Events and Aligned Natural Text

NEURIPS 2023arXiv

citations

MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval

CVPR 2025arXiv

citations

Conformal Linguistic Calibration: Trading-off between Factuality and Specificity

NEURIPS 2025arXiv

citations

From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question-Answering

ICLR 2025arXiv

citations

SpectR: Dynamically Composing LM Experts with Spectral Routing

COLM 2025arXiv

citations

Benjamin Van Durme

papers (20)

Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation

Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning

Rank1: Test-Time Compute for Reranking in Information Retrieval

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

Data Portraits: Recording Foundation Model Training Data

Zero and Few-shot Semantic Parsing with Ambiguous Inputs

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements

Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images

BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing

Ambiguous Images With Human Judgments for Robust Visual Event Classification

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval

MultiVENT: Multilingual Videos of Events and Aligned Natural Text

MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval

Conformal Linguistic Calibration: Trading-off between Factuality and Specificity

SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses

Always Tell Me The Odds: Fine-grained Conditional Probability Estimation

WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment

From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question-Answering

SpectR: Dynamically Composing LM Experts with Spectral Routing

papers (20)

Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation

Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning

Rank1: Test-Time Compute for Reranking in Information Retrieval

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

Data Portraits: Recording Foundation Model Training Data

Zero and Few-shot Semantic Parsing with Ambiguous Inputs

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements

Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images

BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing

Ambiguous Images With Human Judgments for Robust Visual Event Classification

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval

MultiVENT: Multilingual Videos of Events and Aligned Natural Text

MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval

Conformal Linguistic Calibration: Trading-off between Factuality and Specificity

SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses

Always Tell Me The Odds: Fine-grained Conditional Probability Estimation

WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment

From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question-Answering

SpectR: Dynamically Composing LM Experts with Spectral Routing