Searcharxiv⌕ Search

SEARCH · Searcharxiv

Search Searcharxiv

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 199 records · Page 11Linked to original sources
arXiv2026

What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models

Large language models (LLMs) are increasingly used as primary knowledge sources, yet their epistemic diversity - defined as the diversity of real-world claims in their outputs - has never been measured. Low epistemic diversity would pose a risk of knowledge collapse as homogeneous LLMs mediate a shrinking in the range of accessible information over time. The dominant paradigm is that overall LLM diversity is low, but this is always with respect to a single point in time, with no reference baseline or consideration for variation across countries. We address this gap in knowledge by performing the first systematic study of epistemic diversity in LLMs across time and cultural context, testing 27 LLMs on 155 topics covering 12 countries, resulting in 1.7M responses and 70M individual claims. We find that epistemic diversity has increased substantially over the past three years, a positive counter to recent diversity pessimism. However, despite progress, we find that every system is less diverse than a search baseline. This gap is not uniform: RAG can improve diversity, while large models are counterintuitively less diverse than smaller ones. Moreover, LLM parametric knowledge systematically reflects English over local-language knowledge for country specific topics. Together, these results demonstrate that while progress on epistemic diversity is tangible, it is insufficient and unevenly distributed.

cs.CL↗
arXiv2026

Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature

Tracing connections between historical texts is an important part of intertextual research, enabling scholars to reconstruct the virtual library of a writer and identify the sources influencing their creative process. These intertextual links manifest in diverse forms, ranging from direct verbatim quotations to subtle allusions and paraphrases disguised by morphological variation. Language models offer a promising path forward due to their capability of capturing semantic similarity beyond lexical overlap. However, the development of new methods for this task is held back by the scarcity of standardized benchmarks and easy-to-use datasets. We address this gap by introducing Loci Similes, a benchmark for Latin intertextuality detection comprising a curated dataset of ~176k text segments and 1,490 expert-verified parallels, including 945 labeled references from an existing dataset. Using this data, we establish baselines for retrieval and classification of intertextualities with both lexical methods and pretrained encoder language models.

cs.IR↗
arXiv2026

Multi-Source Retrieval and Reasoning for Legal Sentencing Prediction

Legal judgment prediction (LJP) aims to predict judicial outcomes from case facts and typically includes law article, charge, and sentencing prediction. While recent methods perform well on the first two subtasks, legal sentencing prediction (LSP) remains difficult due to its need for fine-grained objective knowledge and flexible subjective reasoning. To address these limitations, we propose $MSR^2$, a framework that integrates multi-source retrieval and reasoning in LLMs with reinforcement learning. $MSR^2$ enables LLMs to perform multi-source retrieval based on reasoning needs and applies a process-level reward to guide intermediate subjective reasoning steps. Experiments on two real-world datasets show that $MSR^2$ improves both accuracy and interpretability in LSP, providing a promising step toward practical legal AI. Our code is available at https://github.com/cjj826/MSR2.

cs.IR↗
arXiv2026

HeMix: Scaling Industrial Ranking Models with Heterogeneous Token Mixing

Scaling up ranking models for industrial recommender systems faces two critical challenges: (C1) existing sequence tokenization fails to jointly capture context-aware and context-invariant user intent from heterogeneous behavior sources, and (C2) prevailing interaction mechanisms are both computationally expensive and semantically homogeneous, limiting prediction quality under strict online latency constraints. We propose \textbf{HeMix}, a scalable ranking model that unifies query-mixed sequence tokenization with heterogeneous feature interaction. To address (C1), HeMix introduces a \textit{Query-Mixed Interest Extraction} module that employs dynamic and fixed queries to simultaneously model context-aware and context-invariant interests from global and real-time behavior sequences. To address (C2), we design the \textit{HeteroMixer} block, comprising Multi-Head Token Fusion, Heterogeneous Mixed-Token Interaction and Group-Aligned Reconstruction, as an efficient alternative to self-attention that enables multi-granularity cross-feature modeling at linear cost. Crucially, HeMix scales smoothly from ${\sim}100$M to ${\sim}1500$M parameters by independently expanding block depth and token dimension, yielding steady accuracy gains without architectural redesign. Experiments on industrial-scale data show that HeMix achieves $+1.64\%$ relative CTR-AUC over the DLRM baseline at the ${\sim}100$M scale while requiring fewer GFLOPs than the strongest competitor. Deployed on the AMAP APP, HeMix yields +0.88\% GMV, +2.74\% PV\_CTR and +0.84\% UV\_CVR over the production baseline in online A/B tests.

cs.IR↗
arXiv2026

GeoGR: Enabling Spatio-Temporal Aware Industrial-scale Generative POI Recommendations

Next Point-of-Interest (POI) prediction is a fundamental task in location-based services (LBS), especially critical for large-scale navigation platforms such as AMAP that serve billions of users in diverse lifestyle scenarios. Although recent POI recommendation approaches based on SIDs have achieved promising performance, they struggle in complex, sparse real-world environments due to two key limitations: (1) inadequate modeling of high-quality SIDs that capture cross-category spatio-temporal collaborative relationships, and (2) poor alignment between large language models (LLMs) and the POI recommendation task. To this end, we propose GeoGR, a geographic generative recommendation framework tailored for navigation-based LBS like AMAP, which perceives changes in users' contextual states and enables spatio-temporal aware POI recommendation. GeoGR features a two-stage design: (i) a geo-aware SID tokenization pipeline that explicitly learns spatio-temporal collaborative semantic representations via geographically constrained co-visited POI pairs, contrastive semantic representation learning, and iterative refinement; and (ii) a multi-stage LLM training strategy that aligns non-native SID tokens through continued pre-training with multiple prompt templates and enables autoregressive POI generation via supervised fine-tuning. Extensive experiments on multiple real-world datasets demonstrate GeoGR superiority over state-of-the-art baselines. Moreover, the deployment on the large-scale AMAP platform over three months, serving millions of users and delivering significant online gains of +2.91% in WINRATE and +5.55% in PV_CTR, confirms its practical effectiveness and scalability in production.

cs.IR↗
arXiv2026

MICE: Minimal Interaction Cross-Encoders for efficient Re-ranking

In Information Retrieval (IR), cross-encoders deliver state-of-the-art ranking effectiveness but have a high inference cost, limiting their use to second-stage re-rankers. Prior work has addressed this bottleneck from two largely separate directions: accelerating cross-encoder inference through attention sparsification, or improving first-stage retrieval effectiveness to alleviate the need of a re-ranker, using more complex models, e.g. late-interactions. In this work, we bridge these two directions through an in-depth analysis of cross-encoder internal mechanisms. By identifying and removing superfluous interactions, we derive MICE (Minimal Interaction Cross-Encoders), a new cross-encoder architecture that retains effectiveness while reducing computational overhead. Extensive evaluations show MICE retains most of the performances of its cross-encoder counterparts in-domain and matches or even exceeds it in out-of-domain, while reducing FLOPs down to 2.5 times.

cs.IR↗
arXiv2026

UniFAR: A Unified Facet-Aware Retrieval Framework for Scientific Documents

Scientific document retrieval (SDR) plays a critical role in modern scientific research, supporting knowledge discovery and evidence-based reasoning. It has evolved along two paradigms: document--document (doc-doc) retrieval driven by inter-document contrastive learning, and question--document (q-doc) retrieval emerging from LLMs and RAG for natural-language interaction. In practice, scientific workflows rely on both paradigms, requiring retrieval of related papers given a seed document and identifying relevant documents given a user question. However, existing methods typically treat these paradigms separately, hindering their complementary strengths. To address this, we propose UniFAR, a unified facet-aware retrieval framework that jointly supports doc-doc and q-doc retrieval within a shared representation space. UniFAR introduces a multi-granularity representation and aggregation module to unify the encoding of short questions and long documents, and a facet-level modeling mechanism with learnable anchors to capture structured semantic roles and complex user intents. It further adopts a facet-aware joint training strategy that integrates doc-doc and q-doc contrastive objectives with facet-level alignment, enabling unified learning from both inter-document relations and question-oriented supervision. Experiments on three benchmark datasets under both doc-doc and q-doc settings across multiple backbone models show that UniFAR consistently outperforms strong baselines and generalizes effectively across different backbones.

cs.IR↗
arXiv2026

APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay

LLM agents rerun full reasoning for every task, even one they solved moments earlier. We introduce \textbf{APEX-EM}, a non-parametric experience memory that stores complete procedural-episodic traces in a typed Procedural Knowledge Graph (PKG) and retrieves them through three channels: semantic search, structural-signature matching over abstract operation sequences, and graph traversal. A Plan-Retrieve-Generate-Iterate-Ingest (PRGII) workflow produces, quality-gates, and commits experiences, indexing both successes and failures so the agent learns what to reuse and what to avoid. No weights change during deployment. We evaluate on five benchmarks: BigCodeBench, KGQAGen-10k, HLE, Lifelong Agent Bench, and ALFWorld. Because prior work uses different backbones, we base our claims on same-backbone comparisons that hold model capability fixed. On held-out BigCodeBench transfer with a shared GPT-4o backbone, APEX-EM gains +7.6\,pp over the no-memory baseline, $3.3\times$ MemRL's +2.3\,pp under the identical setup. On Lifelong Agent Bench with a shared GPT-4o-mini backbone, it gains +1.4\,pp (OS) and +1.0\,pp (DB) cumulative success. On KGQAGen-10k, frozen memory transfers to a blind 1{,}079-question test split at 73.7\% versus 42.0\% with no memory, approaching an oracle handed the ground-truth subgraph (84.9\%). Across three Opus scales the memory gain stays at +27 to +32\,pp, so it adds to model capability rather than substituting for it. Component analysis shows no single mechanism dominates: teacher feedback is negligible for code but adds +10.3\,pp on structured queries, structural signatures give $3.3\times$ the transfer of semantic-only retrieval, and within-epoch iteration recovers most of the gain when rich feedback is unavailable. These results argue for modular memory composed per domain.

cs.CL↗
arXiv2026

LexPath: A domain-oriented multi-path framework for legal article retrieval

Legal article retrieval is critical for building traceable and reliable legal AI systems, where conclusions must be grounded in specific legal articles. However, general-purpose retrieval methods rely heavily on lexical or semantic similarity, making it difficult to distinguish legally relevant articles from textually similar but legally inapplicable ones, particularly when they differ in their underlying legal intent. To bridge this gap, we propose LexPath, a domain-oriented multi-path framework comprising a multi-path retrieval module and an intent-aware reranking module. The retrieval module combines two complementary domain-specific paths to collect candidate articles: an IRAC-guided sparse path that expands queries with legally informative keywords, and a structure-guided dense path trained with hard negatives derived from legal hierarchy and citation relations. The reranking module further refines candidate rankings by incorporating the intent compatibility between queries and legal articles. We evaluate LexPath on three Chinese benchmarks spanning diverse query scenarios and further assess its cross-jurisdictional applicability on a Japanese benchmark. Experimental results demonstrate that LexPath consistently outperforms lexical, dense, hybrid, and adaptive retrieval-augmented generation (RAG) baselines across all four benchmarks. Ablation studies further verify the effectiveness of each component. The data and code are available at https://github.com/wxliuabigail/LexPath.

cs.IR↗
arXiv2026

Exploring Autonomous Agentic Data Engineering for Model Specialization

Large Language Models (LLMs) have demonstrated strong performance on general tasks, while often struggling to adapt to specialized domains without high-quality domain-specific data. Existing LLM-based data curation methods primarily rely on human-designed workflows, leaving it unexamined whether LLMs can autonomously execute an end-to-end data engineering pipeline for model specialization. We formalize Autonomous Agentic Data Engineering, a novel task designed to evaluate LLMs as autonomous data engineers that drive model specialization through end-to-end data curation. We frame data as an optimizable component and study agents that plan, generate, and iteratively optimize training data across multiple domains, guided by post-training performance improvement. Experiments show that autonomous LLM data engineers yield substantial gains, as GPT-5.2 constructs a training curriculum that improves a student model by 57.29%, entirely through iterative, agent-driven data adaptation. By illuminating both potential and bottlenecks, our study establishes autonomous data engineering as a measurable capability and charts a path toward agent-driven model specialization (Code will be released at https://github.com/zjunlp/DataAgent).

cs.CL↗
arXiv2026

From Prompt to Purchase: How AI Brand Recommendations Move Consumers on the Open Web

When a conversational assistant recommends a brand to a user with no recent observed engagement, that user's same-name Google search rises $+4.3$ percentage points (pp) [$3.1$, $5.5$], visits to the brand's own site $+2.4$ pp [$1.4$, $3.5$], and brand-specific retailer-page visits $+1.0$ pp [$0.3$, $1.7$] over matched backward placebos. Recovering that estimate is the work. The mention creates a brand exposure no web log attributes to the assistant, and the naive all-mention funnel that seems to measure it is confounded: many mentions are incidental references to brands the user already uses ("your Netflix download"), whose downstream visits are that existing customer's own behavior and surface as a brand-specific pre-trend. We measure off-platform response on a panel that joins opt-in clickstream to the same users' ChatGPT, Claude, and Gemini conversations, and isolate the effect with a pre-trend event study, a stance classifier, non-customer conditioning, and a within-response same-category control: incidental name-drops then move behavior far less ($+1.8/+1.1/+0.3$), and the named brand moves far more than unnamed same-category brands in the same response. The downstream path is mostly search-mediated and reaches both own sites and retailer pages, with a destination mix that tracks baseline brand-directed behavior rather than redirecting toward either. The design is observational and we do not observe transactions, so retail is purchase-adjacent. Standard referrer-based and last-click measurement miss this upstream exposure: assistants move observably-unengaged users into open-web brand navigation along a path attributed elsewhere -- an acquisition touchpoint at the head of the customer journey that journey models and last-click attribution do not see.

cs.CY↗
arXiv2026

Rethinking Fairness in LLM-Based Recommender Systems: A Survey

Large Language Models (LLMs) are reshaping recommender systems by enabling more semantic, generative, and interactive recommendation pipelines. However, this shift also introduces new fairness challenges, as biases may arise from pretrained knowledge, prompts, generated explanations, decoding strategies, and feedback loops. This survey provides a systematic review of fairness in LLM-based recommender systems (LLM4Rec), organizing existing studies through a two-dimensional view of bias mechanisms and fairness targets, together with a structured overview of the evaluation landscape and mitigation strategies. We further connect fairness with broader trustworthy concerns, including explainability, privacy, robustness, and controllability. To the best of our knowledge, this is the first survey specifically focused on fairness in LLM4Rec, aiming to provide a structured foundation for future research on comprehensive and reliable fairness evaluation in LLM4Rec.

cs.IR↗
arXiv2026

SPARC: Sequence-aware Progressive Attribute Routing and Compression Framework for Generative Recommendation

Generative recommendation tokenizes items as discrete Semantic IDs (SIDs) and autoregressively generates target items from users' historical SID sequences. Although existing SIDs incorporate multimodal and structured information, they are typically statically assigned and independent of the current interaction context. In industrial scenarios, each behavior also contains heterogeneous attributes, such as category, brand, price, behavior type, and timestamp. Fully expanding these features greatly increases the input length, while directly compressing them into a single representation may prematurely discard context-relevant information. We propose \textbf{SPARC}, \uline{\textbf{S}}equence-aware \uline{\textbf{P}}rogressive \uline{\textbf{A}}ttribute \uline{\textbf{R}}outing and \uline{\textbf{C}}ompression Framework for Generative recommendation. SPARC first models the sequential dependencies of each field type to obtain context-aware field representations. It then routes the original, contextual, and identity representations of different fields into multiple slots to preserve complementary information under a fixed capacity. Finally, lightweight cross-item interaction integrates the intermediate tokens and compresses each historical item into a single token. Following the principle of contextualizing before compression, SPARC enriches user-history representations without increasing the input length of the generative backbone. Experiments on industrial Taobao and public Amazon datasets demonstrate that SPARC outperforms strong conventional and generative baselines. Further comparisons with static compression variants show that the improvement of SPARC comes from context-conditioned information retention rather than merely increasing the expressiveness of the compression module.

cs.IR↗
arXiv2026

Query Expansion Should Be Coordinated: Dense Expands, Sparse Anchors

Retrieval-augmented generation (RAG) systems rely on retrieval modules to ground large language model (LLM) outputs. LLM-based query expansion enriches retrieval with document-like passages, but evaluations of hybrid retrieval often fuse fixed top-L prefixes of dense and sparse rankings. Because L controls cross-channel contributions and ranking access, it can alter measured expansion gains. We therefore evaluate complete-list effectiveness and record per-channel replay stopping depths required to certify the ordered top-K. This changes the design: because both rankings determine the fused result, their query constructions should be coordinated rather than designed independently. We present DESA (Dense Expansion and Sparse Anchoring), which shares generated references across channels but specializes their integration. Orthogonal residual expansion adds new semantic directions to the dense query, whereas score-product anchoring reorders the original sparse support without admitting expansion-only matches. The same references thus play complementary roles: Dense expands; Sparse anchors. Across seven BEIR datasets, DESA improves nDCG@10 and Recall@20 over the unexpanded query by 3.82% and 2.38%, while reducing dense and sparse replay stopping depths by 36.90% and 36.56%.

cs.IR↗
arXiv2026

ExecRubrics: Executable Tool-Augmented Rubrics for Verifiable and Efficient Long-Form Evaluation

Rubrics aim to make language-model evaluation transparent by decomposing response quality into interpretable criteria. However, natural-language rubrics are often ambiguous, require LLM judges, and typically assume criteria aggregated through linear weighted sums, limiting their ability to capture dependencies, alternatives, penalties, and override conditions. We propose ExecRubrics, a framework for representing rubrics as compact executable programs. ExecRubrics encodes evaluation logic as verifiable Python scoring functions, giving natural-language rubric intent an operational semantics: a fixed decision procedure that can be inspected, executed, and edited. On three long-form response benchmarks -- HealthBench, HelpSteer, and ArgQuality -- we show that ExecRubrics can recover substantial preference signal without an LLM judge at evaluation time. On ArgQuality and HelpSteer, the strongest executable variants are within 1.1 and 4 percentage points, respectively, of the direct GPT-5.5 agentic baseline. Executable rubrics are also considerably faster, achieving a 192x average speedup. We show that incorporating external logic and resources from text processing libraries such as NLTK and spaCy can further improve preference accuracy. Our results suggest a novel way of approaching automated evaluation, by offering a faster, more explainable, and less ambiguous alternative to black-box rubric evals, particularly in high-stakes domains such as healthcare and banking where precision and auditability are critical.

cs.AI↗
arXiv2026

HubMixer: Progressive Latent Hub Mixing for Parameter-Efficient Feature Interaction in Recommendation

Learning effective feature interactions is central to industrial recommendation and advertising ranking systems. Recent token-mixing architectures simplify self-attention with lightweight mixing operators, improving hardware efficiency and enabling large-scale deployment. However, recommendation tokens are fundamentally heterogeneous: user profiles, item attributes, behavioral sequences, context features, statistical signals, and business-side features live in different semantic spaces and interact in sparse, sample-specific patterns. Directly mixing all tokens in the raw heterogeneous token space may therefore be parameter-inefficient, as the model must implicitly discover which feature groups should interact and how such interactions should be routed. In the paper, we propose HubMixer, a parameter-efficient latent hub mixing architecture for feature interaction in recommendation. Instead of directly mixing raw feature tokens, HubMixer introduces a small set of learnable latent hubs to organize feature interactions through an `induction--interaction--readout` paradigm. First, hub induction summarizes heterogeneous tokens into compact latent hubs, where latent hubs query input tokens through cross-attention. Second, hub interaction performs high-order interaction in the cleaner latent hub space. Third, token-conditioned readout lets each original token selectively read from the interacted hubs, injecting global interaction semantics while preserving token-level field identity. Extensive offline experiments on industrial recommendation tasks show that HubMixer outperforms the SOTA models. Online A/B testing in the Kuaishou short-video recruitment business further shows a statistically significant 5.48% improvement in resume submission conversion rate, and HubMixer has been fully deployed in production.

cs.IR↗
arXiv2026

Understanding before verifying: Claim normalization for automated citation verification

Citation accuracy has been studied for decades because of its importance to research reliability. Content-level citation verification assesses the reliability of scholarly claims. Recent work adopts a two-stage retrieval-classification framework inherited from fact-checking. However, this design overlooks the complexity of the raw citing claim and introduces three issues into the verification system, namely scope mismatch, perspective mismatch, and proposition entanglement. These issues increase the difficulty of retrieval and classification, thereby limiting model performance. Motivated by this gap, we propose claim normalization, which applies three rewriting strategies to the raw citing claim before retrieval and classification, allowing each downstream model to perform a single, well-defined task. Building on this method, we develop Claim-Normalized Citation Verification (CNCV), a new three-stage framework consisting of claim normalization, evidence retrieval with grounding, and citation classification. We evaluate CNCV across 18 classifiers using a factorial experiment on human-annotated citation instances. Compared with the prior two-stage framework, CNCV improves macro F1 by an average of 12% for encoders and 10% for generative LLMs, driven by improved evidence quality, the dominant factor identified in our experiments. Evidence retrieved from automatically normalized claims yields downstream classification performance statistically equivalent to that obtained with manually annotated evidence.

cs.IR↗
arXiv2026

Doc-REFRAG: Rethinking Multimodal Document Retrieval-Augmented Generation

Real-world knowledge resides in multimodal documents, necessitating retrieval-augmented generation (RAG) for accurate question answering. However, existing multimodal RAG models are primarily designed for single-image or closed-document settings and exhibit limited accuracy in realistic multi-image scenarios. Moreover, processing numerous retrieved images incurs substantial computational overhead from irrelevant visual tokens. To address these challenges, we introduce DocLongRAG, a large-scale dataset of 343K question--answer pairs, each associated with an average of 37.4 retrieved images to reflect authentic RAG workflows. Building on this dataset, we propose Doc-REFRAG, a question-guided framework that compresses visual tokens into coarse chunks and selectively expands question-relevant ones via a lightweight RL-based selector. Experiments on six benchmarks show that Doc-REFRAG outperforms eleven strong baselines, achieving state-of-the-art accuracy with significantly lower inference latency. Our resources are available at https://github.com/Collab-Gen/Doc-REFRAG.

cs.IR↗