Retrieval-augmented generation to improve math question-answering: Trade-offs between groundedness and human preference
For middle-school math students, interactive question-answering (QA) with tutors is an
effective way to learn. The flexibility and emergent capabilities of generative large language …
effective way to learn. The flexibility and emergent capabilities of generative large language …
Annotating Data for Fine-Tuning a Neural Ranker? Current Active Learning Strategies are not Better than Random Selection
Search methods based on Pretrained Language Models (PLM) have demonstrated great
effectiveness gains compared to statistical and early neural ranking models. However, fine …
effectiveness gains compared to statistical and early neural ranking models. However, fine …
Resources for Combining Teaching and Research in Information Retrieval Coursework
The first International Workshop on Open Web Search (WOWS) was held on Thursday,
March 28th, at ECIR 2024 in Glasgow, UK. The full-day workshop had two calls for …
March 28th, at ECIR 2024 in Glasgow, UK. The full-day workshop had two calls for …
Validating synthetic usage data in living lab environments
Evaluating retrieval performance without editorial relevance judgments is challenging, but
instead, user interactions can be used as relevance signals. Living labs offer a way for small …
instead, user interactions can be used as relevance signals. Living labs offer a way for small …
LongEval-Retrieval: French-English Dynamic Test Collection for Continuous Web Search Evaluation
LongEval-Retrieval is a Web document retrieval benchmark that focuses on continuous
retrieval evaluation. This test collection is intended to be used to study the temporal …
retrieval evaluation. This test collection is intended to be used to study the temporal …
[PDF][PDF] Longeval-retrieval: French-english dynamic test collection for continuous web search evaluation
P Galuščáková, R Deveaud… - arXiv preprint arXiv …, 2023 - ufal.mff.cuni.cz
ABSTRACT LongEval-Retrieval is a Web document retrieval benchmark that focuses on
continuous retrieval evaluation. This test collection is intended to be used to study the …
continuous retrieval evaluation. This test collection is intended to be used to study the …
[PDF][PDF] Leveraging prior relevance signals in web search
This work reports our participation in the retrieval task of the second LongEval lab iteration at
CLEF 2024. As part of this year's contribution, we analyze to which extent prior relevance …
CLEF 2024. As part of this year's contribution, we analyze to which extent prior relevance …
[PDF][PDF] Reproducible Information Retrieval Research: From Principled System-Oriented Evaluations Towards User-Oriented Experimentation
T Breuer - 2023 - duepublico2.uni-due.de
The reproducibility of earlier findings is fundamental to the empirical sciences. Even though
this circumstance is widely acknowledged, several systematic large-scale reproducibility …
this circumstance is widely acknowledged, several systematic large-scale reproducibility …
Enriching Simple Keyword Queries for Domain-Aware Narrative Retrieval
Providing effective access paths to content is a key task in digital libraries. Oftentimes, such
access paths are realized through advanced query languages, which, on the one hand …
access paths are realized through advanced query languages, which, on the one hand …
[PDF][PDF] B. 8. JCDL 2023: Enriching Simple Keyword Queries for Domain-Aware Narrative Retrieval
H Kroll - Narrative Information Access–A new Paradigm for …, 2024 - d-nb.info
Providing effective access paths to content is a key task in digital libraries. Oftentimes, such
access paths are realized through advanced query languages, which, on the one hand …
access paths are realized through advanced query languages, which, on the one hand …