11 papers
Learning Dynamics of Strategic Publishers in Generative AI Ecosystems
Sagie Dekel, Omer Madmon, Moshe Tennenholtz +1
Generative AI (GenAI) search systems are transforming how users access information. Unlike ranking-based search systems, where users observe a ranked list of documents, GenAI searc…
Stability in Competitive Search with Results Diversification
Itamar Reinman, Omer Madmon, Moshe Tennenholtz +1
In a competitive search setting, publishers strategically modify their documents in response to induced rankings so as to improve their future ranking. We present a novel game-theo…
Predicting the Benefit of Retrieval Augmentation in Open-Domain Question Answering
Or Dado, David Carmel, Oren Kurland
While retrieval augmented generation has become a common approach for enhancing question answering systems, retrieval is not universally advantageous. We study the problem of predi…
Addressing Corpus Knowledge Poisoning Attacks on RAG Using Sparse Attention
Sagie Dekel, Moshe Tennenholtz, Oren Kurland
Retrieval Augmented Generation (RAG) is a highly effective paradigm for keeping LLM-based responses up-to-date and reducing the likelihood of hallucinations. Yet, RAG was recently…
RLRF: Competitive Search Agent Design via Reinforcement Learning from Ranker Feedback
Tommy Mordo, Sagie Dekel, Omer Madmon +2
Competitive search is a setting where document publishers modify them to improve their ranking in response to a query. Recently, publishers have increasingly leveraged LLMs to gene…
On the Merits of LLM-Based Corpus Enrichment
Gal Zur, Tommy Mordo, Moshe Tennenholtz +1
Generative AI (genAI) technologies -- specifically, large language models (LLMs) -- and search have evolving relations. We argue for a novel perspective: using genAI to enrich a do…