Generative recommenders decode items from a user's interaction history, but offer no way for users to correct a recommendation that misses their current intent. Adding conversation is natural since items and words share same output space, yet training the model to converse may overwrite the history-to-item mapping it r...
Yuliia Den, Zhi Rui Tam, Yung-Yu Shih et al.· 0 citations
Large Language Models (LLMs) are increasingly used to enrich user queries in information retrieval (IR) so that a standard retriever such as BM25 can bridge vocabulary gaps with the target corpus. Any single LLM, however, is limited by its training data and architectural biases, and its enrichment behavior depends on h...
Tzu-I Ho, Yung-Yu Shih, Shang-Yu Su et al.· 0 citations
This work revisits incremental GR as an in-context retrieval problem, where newly added documents are supplied as inference-time document-docid evidence and proposes ICICLE, an in-context indexing framework that performs source-aware docid generation over both parametric memory and context-provided document-docid pairs...
Yuliia Den, Yung-Yu Shih, Zhi Rui Tam et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.