Jack Hessel
Researcher at Samaya AI; previously at Allen AI; co-author on WildChat and CLIPScore; works on multimodal evaluation and humor / creativity in LLMs.
- Role
- researcher
- Currently at
- Samaya AI
- twitter.com/jmhessel
- GitHub
- github.com/jmhessel
- Scholar
- scholar.google.com/citations
- Papers
- 22
Cite
Notes
Only stored in your browser.
Authored papers
22WildChat: 1M ChatGPT Interaction Logs in the Wild
ICLR
OLMo: Accelerating the Science of Language Models
arXiv 2024
Selective Vision is the Challenge for Visual Reasoning: A Benchmark for Visual Argument Understanding
arXiv 2024
Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
arXiv 2024
OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
arXiv 2023
Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
arXiv 2023
What's "up" with vision-language models? Investigating their struggle with spatial reasoning
arXiv 2023
Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text
multimodal-c4-an-open-billion-scale-corpus-of
Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step
arXiv 2023
FunQA: Towards Surprising Video Comprehension
arXiv 2023
CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos
ICCV 2023 1
VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use
arXiv 2023
Tailoring Self-Rationalizers with Multi-Reward Distillation
arXiv 2023
Localized Symbolic Knowledge Distillation for Visual Commonsense Models
localized-symbolic-knowledge-distillation-for
Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
arXiv 2022
SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization
arXiv 2022
Multimodal Knowledge Alignment with Reinforcement Learning
arXiv 2022
Quark: Controllable Text Generation with Reinforced Unlearning
arXiv 2022
CLIPScore: A Reference-free Evaluation Metric for Image Captioning
EMNLP 2021 11
Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer
arXiv 2021
Symbolic Knowledge Distillation: from General Language Models to Commonsense Models
NAACL 2022 7
Reframing Human-AI Collaboration for Generating Free-Text Explanations
NAACL 2022 7
Affiliations
Previously
Frequent co-authors
10from 22 papers
Yejin Choi
professor
Youngjae Yu
Ximing Lu
Peter West
Prithviraj Ammanabrolu
Ronan Le Bras
Anas Awadalla
Hannaneh Hajishirzi
professor
Liwei Jiang
Ludwig Schmidt
professor