Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 1105.6213

Using Context to Improve the Evaluation of Information Retrieval Systems

Abdelkrim Bouramoul·Mohamed-Khireddine Kholladi·Bich-Lien Doan
View original source ↗Read source document ↗Export metadata ↓

Abstract

The crucial role of the evaluation in the development of the information retrieval tools is useful evidence to improve the performance of these tools and the quality of results that they return. However, the classic evaluation approaches have limitations and shortcomings especially regarding to the user consideration, the measure of the adequacy between the query and the returned documents and the consideration of characteristics, specifications and behaviors of the search tool. Therefore, we believe that the exploitation of contextual elements could be a very good way to evaluate the search tools. So, this paper presents a new approach that takes into account the context during the evaluation process at three complementary levels. The experiments gives at the end of this article has shown the applicability of the proposed approach to real research tools. The tests were performed with the most popular searching engine (i.e. Google, Bing and Yahoo) selected in particular for their high selectivity. The obtained results revealed that the ability of these engines to rejecting dead links, redundant results and parasites pages depends strongly to how queries are formulated, and to the political of sites offering this information to present their content. The relevance evaluation of results provided by these engines, using the user's judgments, then using an automatic manner to take into account the query context has also shown a general decline in the perceived relevance according to the number of the considered results.

Explore related subjects

cs.IR

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Abdelkrim Bouramoul, Mohamed-Khireddine Kholladi, Bich-Lien Doan. 2011-05-31. Using Context to Improve the Evaluation of Information Retrieval Systems. https://doi.org/10.5121/ijdms.2011.3202

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking

Large language models (LLMs) are increasingly deployed in information systems, including being used as second-stage rerankers in information retrieval pipelines, yet their susceptibility to recency bias has received little attention. We investigate whether LLMs implicitly favour newer documents by prepending artificial publication dates to passages in the TREC Deep Learning passage retrieval collections in 2021 (DL21) and 2022 (DL22). Across seven models, GPT-3.5-turbo, GPT-4o, GPT-4, LLaMA-3 8B/70B, and Qwen-2.5 7B/72B, "fresh" passages are consistently promoted, shifting the Top-10's mean publication year forward by up to 4.78 years and moving individual items by as many as 95 ranks in our listwise reranking experiments. Although larger models attenuate the effect, none eliminate it. We also observe that the preference of LLMs between two passages with an identical relevance level can be reversed by up to 25% on average after date injection in our pairwise preference experiments. These findings provide quantitative evidence of a pervasive recency bias in LLMs and highlight the importance of effective bias-mitigation strategies.

cs.IR↗
arXiv2026

UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems

Industrial recommender systems cascade stages with different objectives, feature spaces, and latency constraints. Optimizing pre-ranking and ranking separately induces cross-stage inconsistency: upstream models may filter out items preferred by downstream rankers, while independently tuned downstream fusion can offset upstream improvements. Most existing multi-task fusion methods target the ranking stage alone, and cross-stage methods often align with a downstream-derived score, leaving joint optimization of fusion modules across cascaded stages largely unexplored. We propose UniRec, a Unified Cross-stage Recommendation Fusion model. First, the two fusion agents partially share input embeddings in a single computation graph, allowing gradients from either stage to propagate through the shared representations. Second, a dual-axis preference alignment objective coordinates the two stages: horizontally, a compact aggregation term reorganizes dozens of pairwise objectives over heterogeneous prior signals into bidirectional preference evidence; vertically, a cross-stage consistency term transfers downstream pairwise preferences to the upstream fusion score. Third, we introduce attribute group-relative regularization, which computes relative advantages and normalizes policy updates within each attribute group, ensuring that uniformly promoting all items in a high-reward group provides no additional optimization gain. Offline experiments demonstrate UniRec consistently outperforms single-stage fusion and cross-stage coordination baselines; online A/B experiments show a 0.616% gain in app usage duration. UniRec has been fully deployed on the Kuaishou platform.

cs.IR↗
arXiv2026

Scaling Articulated Rationales for MLLM-based Recommendation

We presented SARA, an industrial framework that transforms sparse articulated user rationales into scalable recommendation signals. Its data engine curates questionnaire responses into SARA-HQ, providing explicit preference supervision for aligning SARA-7B through SFT and Quality-Refining DPO. This alignment extends rationale generation from $86{,}564$ questionnaire-covered authors to the full $10$M-author space. SARA-Ranker translates the generated positive and negative rationales into features for user--author interaction modeling and negative-feedback history modeling, connecting articulated reasons to production ranking. Evaluation on unseen authors demonstrates that SARA-7B generates more specific, relevant, and grounded rationales than the evaluated general-purpose MLLMs. On top of a strong industrial ranking baseline with multimodal features, separate online A/B tests show that positive-rationale integration increases watch time by $0.99\%$, while negative-rationale integration reduces Hate feedback by $8.16\%$. Daily refresh and more than $30$ days of production deployment further demonstrate the operational feasibility of the approach. These findings establish articulated rationales as a useful complement to behavioral and content signals, and demonstrate a practical role for MLLMs in scaling sparse human explanations into preference information that improves industrial recommendation.

cs.IR↗