The strong independent performance of the Harrier-OSS model validates the use of decoder-only architectures for dense ToT retrieval, though the inclusion of simpler models like BM25 proved invaluable for enriching the rewrite training data, outperforming the query-rewrite focused runs published on TREC 2025.
The main implication of this research is the validation of a practical architecture for improving IR systems, offering a viable alternative for domain-specific contexts such as Sequran.
Ray Ramadita, Wisnu Uriawan, W. Zulfikar· 0 citations
Oblique retrieval, as exemplified by OBLIQ-Bench, asks a retriever to find documents whose relevance is determined by a latent attribute (an implicit stance, an analogous reasoning technique, an authorial fingerprint, or a vague tip-of-the-tongue recollection) that has little or no surface expression in the document. S...
Mahmoud Abdalla, Abdelrahman Abdallah, Shaimaa Sedek et al.· 0 citations
This work introduces AnchorQE, a training-free method that separately encodes the original query and its expansion before interpolating them, and shows that AnchorQE improves retrieval effectiveness by up to 12.89% when compared to widely-used expansion-only or text-level concatenation baselines across TREC-DL, LoTTE,...
This work proposes a novel training-free method that generates a very large number of queries with minimal LLM usage by compositionally combining a small set of atomic components and applies LLM reasoning to construct a high-quality document set that balances precision and recall while capturing the user's core intent.
Yunah Jang, Kang-il Lee, Joongbo Shin et al.· 0 citations
This work proposes a two-stage generator-in-the-loop alignment framework that consistently outperforms rank-order, random, and REPLUG-style likelihood baselines under various alignment losses and pool size settings, suggesting that answer-level generator feedback is an effective supervision signal for preference alignm...
Zhang-Yu Chang, Dong-Jun Han, Seyyedali Hosseinalipour et al.· 0 citations
A policy-aligned retrieval framework that improves offline relevance over a matched-capacity baseline, with gains broadly distributed across facet combinations, and serves this framework with a two-stage GPU architecture.
Dhritiman Das, Chujie Zheng, Ronak Kaoshik et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
