3 accepted papers
Current causal discovery methods using Large Language Models (LLMs) often rely on pairwise or iterative strategies, which fail to capture global dependencies, amplify local biases, and reduce overall accuracy. This work introduces a unified framework for one-step full causal graph discovery through:
Cryptocurrency has attracted a lot of public attention and opinion worldwide. Users have different kinds of information needs regarding such topics and publicly available information is a good resource to satisfy those information needs. In this paper, we investigate the public opinion on cryptocurr…
Although Wikipedia is the largest multilingual encyclopedia, it remains inherently incomplete. There is a significant disparity in the quality of content between high-resource languages (HRLs, e.g., English) and low-resource languages (LRLs, e.g., Hindi), with many LRL articles lacking adequate info…