Multi-tenant dense retrieval systems increasingly employ shared compressed indexes where individual tenants adapt embeddings via fine-tuning (e.g., LoRA). While query-side projection adapters bridge the resulting embedding mismatch, a critical design choice remains for the optional reranking stage: should distances be...
Jun Woo Chung, Wei-Jie Zhao· Proceedings of the 20th ACM...· 0 citations
HIVE, which compresses trajectory hidden states, selects informative step-layer evidence, and conditions a verifier through continuous prefix embeddings to produce a hallucination score and structured diagnostics, outperforms eight established baselines and a verifier-backbone-matched text-only control in all six setti...
Guoshenghui Zhao, Wei-Jie Zhao, Tan Yu· arXiv.org· 1 citation
RapidUn, an influence-guided framework that converts cross-sample influence estimates into fixed sample-specific weights for weighted LoRA unlearning, is proposed, and complementary TOFU, semantic LLM-judge, and IFEval evaluations further support the effectiveness of influence-guided sample reweighting beyond the contr...
Hidden diffusion trajectories are established as actionable signals for selective test-time reasoning repair and LOCKR, a hidden-state trajectory-guided planner that decides when to allocate additional computation, expands a structured set of targeted repair branches, and selects the most promising continuation using t...
Guoshenghui Zhao, Tan Yu, Wei-Jie Zhao· 0 citations
This work presents TiGER (Time-Integrated Graph for Efficient Retrieval), a novel approach for performing fast time-aware approximate nearest neighbor searches on dynamic vector datasets with flexibility over any possible time range by leveraging an index structure based on integrated versioned connectivity.
Jun Woo Chung, Wei-Jie Zhao· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
