jlin816/rewards-from-language
Code and data for "Inferring Rewards from Language in Context" [ACL 2022].
This project helps build intelligent systems that can understand a user's underlying preferences, not just their direct commands. By analyzing how people phrase requests, it can infer their general likes and dislikes. This allows the system to make better decisions in new situations, acting more like a helpful assistant than a simple instruction-follower. It's designed for researchers and developers working on AI agents or recommendation systems who want to build more intuitive and adaptive user experiences.
No commits in the last 6 months.
Use this if you are developing AI systems that need to learn user preferences from natural language to predict optimal actions in varied scenarios, beyond just direct commands.
Not ideal if you only need to process direct, unambiguous instructions where user preferences are not a factor in decision-making.
Stars
16
Forks
—
Language
Python
License
MIT
Category
Last pushed
May 22, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/jlin816/rewards-from-language"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
yxuansu/SimCTG
[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation
alibaba-edu/simple-effective-text-matching
Source code of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Shark-NLP/OpenICL
OpenICL is an open-source framework to facilitate research, development, and prototyping of...