5 papers
Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using Implicit Feedback from Users
Haw-Shiuan Chang, Jeffrey Gomez, Mehul Patwari +2
To align a Large Language Model (LLM), most existing methods collect explicit human feedback and train a reward model to predict the human preference based on the response text. Th…
Scaling Laws for Cross-Encoder Reranking
Rahul Seetharaman, Aman Bansal, Hamed Zamani +1
Scaling laws are well studied for language models and first-stage retrieval, but not for reranking. We present the first systematic study of scaling laws for cross-encoder reranker…
Reliable Annotations with Less Effort: Evaluating LLM-Human Collaboration in Search Clarifications
Leila Tavakoli, Hamed Zamani
Despite growing interest in using large language models (LLMs) to automate annotation, their effectiveness in complex, nuanced, and multi-dimensional labelling tasks remains relati…
Understanding Modality Preferences in Search Clarification
Leila Tavakoli, Giovanni Castiglia, Federica Calo +3
This study is the first attempt to explore the impact of clarification question modality on user preference in search engines. We introduce the multi-modal search clarification dat…
Online and Offline Evaluation in Search Clarification
Leila Tavakoli, Johanne R. Trippas, Hamed Zamani +2
The effectiveness of clarification question models in engaging users within search systems is currently constrained, casting doubt on their overall usefulness. To improve the perfo…