Alert button
Picture for Mari Ostendorf

Mari Ostendorf

Alert button

OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking

Nov 16, 2023
Chia-Hsuan Lee, Hao Cheng, Mari Ostendorf

Viaarxiv icon

DIALGEN: Collaborative Human-LM Generated Dialogues for Improved Understanding of Human-Human Conversations

Jul 13, 2023
Bo-Ru Lu, Nikita Haduong, Chia-Hsuan Lee, Zeqiu Wu, Hao Cheng, Paul Koester, Jean Utke, Tao Yu, Noah A. Smith, Mari Ostendorf

Figure 1 for DIALGEN: Collaborative Human-LM Generated Dialogues for Improved Understanding of Human-Human Conversations
Figure 2 for DIALGEN: Collaborative Human-LM Generated Dialogues for Improved Understanding of Human-Human Conversations
Figure 3 for DIALGEN: Collaborative Human-LM Generated Dialogues for Improved Understanding of Human-Human Conversations
Figure 4 for DIALGEN: Collaborative Human-LM Generated Dialogues for Improved Understanding of Human-Human Conversations
Viaarxiv icon

Building blocks for complex tasks: Robust generative event extraction for radiology reports under domain shifts

Jun 15, 2023
Sitong Zhou, Meliha Yetisgen, Mari Ostendorf

Viaarxiv icon

Fine-Grained Human Feedback Gives Better Rewards for Language Model Training

Jun 02, 2023
Zeqiu Wu, Yushi Hu, Weijia Shi, Nouha Dziri, Alane Suhr, Prithviraj Ammanabrolu, Noah A. Smith, Mari Ostendorf, Hannaneh Hajishirzi

Figure 1 for Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Figure 2 for Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Figure 3 for Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Figure 4 for Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Viaarxiv icon

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

Mar 28, 2023
Yushi Hu, Benlin Liu, Jungo Kasai, Yizhong Wang, Mari Ostendorf, Ranjay Krishna, Noah A. Smith

Figure 1 for TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering
Figure 2 for TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering
Figure 3 for TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering
Figure 4 for TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering
Viaarxiv icon

One Embedder, Any Task: Instruction-Finetuned Text Embeddings

Dec 20, 2022
Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, Mari Ostendorf, Wen-tau Yih, Noah A. Smith, Luke Zettlemoyer, Tao Yu

Figure 1 for One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Figure 2 for One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Figure 3 for One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Figure 4 for One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Viaarxiv icon

Binding Language Models in Symbolic Languages

Oct 06, 2022
Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li, Rahul Nadkarni, Yushi Hu, Caiming Xiong, Dragomir Radev, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, Tao Yu

Figure 1 for Binding Language Models in Symbolic Languages
Figure 2 for Binding Language Models in Symbolic Languages
Figure 3 for Binding Language Models in Symbolic Languages
Figure 4 for Binding Language Models in Symbolic Languages
Viaarxiv icon

Selective Annotation Makes Language Models Better Few-Shot Learners

Sep 05, 2022
Hongjin Su, Jungo Kasai, Chen Henry Wu, Weijia Shi, Tianlu Wang, Jiayi Xin, Rui Zhang, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, Tao Yu

Figure 1 for Selective Annotation Makes Language Models Better Few-Shot Learners
Figure 2 for Selective Annotation Makes Language Models Better Few-Shot Learners
Figure 3 for Selective Annotation Makes Language Models Better Few-Shot Learners
Figure 4 for Selective Annotation Makes Language Models Better Few-Shot Learners
Viaarxiv icon

INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions

Jul 02, 2022
Zeqiu Wu, Ryu Parish, Hao Cheng, Sewon Min, Prithviraj Ammanabrolu, Mari Ostendorf, Hannaneh Hajishirzi

Figure 1 for INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions
Figure 2 for INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions
Figure 3 for INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions
Figure 4 for INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions
Viaarxiv icon