Project CARE

The repository for training-evaluation code and other resources to replicate experiments in "Reward Modeling for Scientific Writing Evaluation"

Code associated with paper - Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review

This repository contains the code for our paper "Reviewing the Reviewer: Elevating Peer Review Quality through LLM-Guided Feedback"

The repository contains the codes for our paper "Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue"

Repository for "Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity" (https://arxiv.org/abs/2508.07902)

Code associated with the preprint: "M4FC: a Multimodal, , Multilingual, Multicultural, Multitask real-world Fact-Checking Dataset"

Code and datasets accompanying the arXiv preprint: "Protecting multimodal large language models against misleading visualizations"

Project CARE - NLP Broker

A curated collection of papers, datasets, and resources on the topic of misleading chart understanding