6 papers
On Improving Faithfulness of Podcasts from Documents
Soumya Dutta, Tejas Indulal Dhamecha, Pannaga Shivaswamy
Large language models (LLMs) are increasingly used to generate long-form conversational content such as podcasts from textual sources. While these systems produce fluent and engagi…
A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks
Ishani Mondal, Aparna Garimella, Ananya Sai +2
Automatically generated videos from scientific papers are increasingly used for education and research dissemination. However, existing evaluation metrics mainly measure visual qua…
CATTO: Balancing Preferences and Confidence in Language Models
Nisarg Parikh, Ananya Sai, Pannaga Shivaswamy +2
Large language models (LLMs) often make accurate next token predictions but their confidence in these predictions can be poorly calibrated: high-confidence predictions are frequent…
What is in a name? Mitigating Name Bias in Text Embeddings via Anonymization
Sahil Manchanda, Pannaga Shivaswamy
Text-embedding models often exhibit biases arising from the data on which they are trained. In this paper, we examine a hitherto unexplored bias in text-embeddings: bias arising fr…
POSIT: Promotion of Semantic Item Tail via Adversarial Learning
Qiuling Xu, Pannaga Shivaswamy, Xiangyu Zhang
In many recommendations, a handful of popular items (e.g., movies / television shows, news, etc.) can be dominant in recommendations for many users. However, we know that in a larg…
ExCalibR: Expected Calibration of Recommendations
Pannagadatta Shivaswamy
In many recommender systems and search problems, presenting a well balanced set of results can be an important goal in addition to serving highly relevant content. For example, in…