Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.23346

Jev-as-a-Judge for Brazilian Portuguese Information Retrieval: Relevance Assessment and Reranking

Leandro Carísio Fernandes·Jayr Pereira
View original source ↗Read source document ↗Export metadata ↓

Abstract

This study investigates Jev, a System One model designed for fast, structured decision-making, in information retrieval. We use Jev-as-a-judge to generate relevance judgments for four Brazilian Portuguese IR collections covering different domains and compare them with the official relevance judgments of each collection. We also evaluate Jev as a reranker. For relevance assessment, exact agreement ranged from 52.9% to 64.9%, while quadratic weighted Cohen's kappa ranged from 0.52 to 0.82. Most disagreements involved adjacent relevance levels, with at least 94.5% of annotations matching exactly or differing by only one relevance level. Despite differences at the individual query--document level, Jev-generated qrels produced similar retrieval system rankings, with Kendall's tau ranging from 0.90 to 0.93 for NormasTCU and Ulysses-RFCorpus across the two evaluation metrics. For reranking, Jev reordered the top 1,000 BM25 candidates for each of the 50 Quati test queries, increasing nDCG@10 from 0.3329 to 0.6331 (+90.2%) and MRR from 0.6852 to 0.9033 (+31.8%). These findings support Jev as a relevance assessor and show improved ranking effectiveness over BM25 in the evaluated reranking setting.

Explore related subjects

cs.IR

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Leandro Carísio Fernandes, Jayr Pereira. 2026-10-16. Jev-as-a-Judge for Brazilian Portuguese Information Retrieval: Relevance Assessment and Reranking. https://arxiv.org/abs/2610.23346

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

KEEP EXPLORING

Related papers

arXiv2026

Advertising to Agents: Measuring Description-Framing Bias in LLM Tool Selection

AI agents often pick tools from registries, where each provider writes its tool's description; we ask whether sales language there changes which tool an agent picks. We built pairs of listings that differ in one way (praise, a verifiable specification, or list order) and asked two OpenAI models to call one tool. In a preregistered study, stacked praise (four kinds) raised a tool's pick rate by about 43 percentage points, matching or beating a verifiable specification. Praise also pulled some picks toward tools whose numeric limit was too small. With identical listings, the first-listed tool was picked about 72 points more often. Structured fields helped agents pick the capable tool; sales text beside them reduced or erased that gain. An exploratory study of five models shows the same direction; a "Sponsored" label dampened it, and a system-prompt warning moved one model. Registries could list limits as fields, hide sales text from agents, and randomize order. Stacked praise replicated on held-out domains; no single kind did after correcting for multiple tests. Preregistered results are provisional until blind phrase ratings are complete, and cover two small models.

cs.IR↗
arXiv2026

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

Industrial recommender systems use cascaded stages with different candidate spaces, data distributions, and latency constraints. Independently optimizing their multi-task fusion (MTF) modules can cause cross-stage preference inconsistency, while existing cross-stage methods mainly transfer supervision to upstream scoring models and leave fusion modules jointly unoptimized. We propose UniRec, a Unified Cross-stage Recommendation Fusion framework that jointly optimizes pre-ranking and ranking fusion agents. UniRec employs a coupled dual-agent architecture with partially shared embeddings and stage-specific fusion functions. It further introduces Dual-Axis Preference Optimization to combine stage-local preferences with downstream-to-upstream preference transfer. Attribute Group-Relative Regularization (AGRR) mitigates reward-induced distribution drift by normalizing preference advantages within attribute groups. To improve efficiency, Compact Pairwise Preference Aggregation (CPPA) reduces the objective-dependent pairwise complexity, while Confidence-Aware Pair Pruning (CAPP) further reduces the evaluated pair space. Extensive offline and online experiments on a production short-video system demonstrate consistent gains over single-stage fusion and cross-stage coordination baselines. In a nine-week online A/B test, UniRec improves total watch time by $0.675\%$ and app usage time by $0.616\%$, and has been fully deployed in production.

cs.IR↗
arXiv2026

Reasoning Reranking with Semantic IDs as the Sole Item Representation

Reasoning rerankers write a rationale before ranking a candidate slate, and existing systems read item metadata to do so, even though generative recommenders increasingly represent items as compact Semantic IDs (SIDs). Ranking from SIDs alone has two appeals: SID prompts are far shorter than the matched item text, and although item codes are fixed from content, the backbone learns their token embeddings in part from user-item interaction sequences, so the tokens can carry behavioral signal that item text lacks. That training targets next-item generation, and whether it supports ranking a supplied slate from SIDs alone is untested. We build ReRankID, a controlled testbed in which models reason and rank from a history and slate shown only as SIDs, varying item rendering, history length, and slate size one at a time. On this testbed, such models often copy the input order instead of reranking, and readable metadata does not repair the failure. We compare supervised fine-tuning, rejection-sampled self-training, on-policy distillation, and verifier-based reinforcement learning as post-training methods and find that they elicit the missing behavior. The strongest post-trained model, the 8B model trained with a graded ranking reward, gives the best SID-only ranking and matches strong text-reading LLMs whose prompts are about 20x longer. It ranks above random with no history at all, where a caption-reading reference does not, and it keeps its gains at long histories, where text prompts pass 50k tokens and the caption-reading reference stops improving. In a paired rationale audit, this model argues trade-offs better than that reference but describes items less accurately. The common post-training methods we test thus elicit ranking from SIDs but not faithful item descriptions, which calls for post-training that improves the reasoning itself, not only the ranking it produces.

cs.IR↗