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 55 records · Page 3Linked to original sources

arXiv2026

SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching

Modeling long-term user behavior is central to sequential recommendation and billion-scale industrial recommender systems, yet production ranking models operate under strict latency, memory, communication, and training-throughput constraints. At the 100K scale, the challenge extends beyond attention complexity: raw sequence features must be stored, transferred, and repeatedly processed during training and online serving. Existing approaches based on history truncation, multi-stage behavior retrieval, compressed lifelong histories, or train-short/infer-long extrapolation either weaken end-to-end optimization or retain substantial length-dependent cost. We present SequenceO1, an end-to-end framework for ultra-long user behavior sequence modeling, deployed at full traffic on Douyin with histories of up to 100K interactions. SequenceO1 follows a compress-then-reason design. Its Sketch Attention (SA) uses learnable prototypes and prototype-wise normalization to compress the raw history into a fixed-size, target-agnostic user representation. Target-conditioned Stacked Target-to-History Cross Attention (STCA) then models complementary time scales: a recent 10K suffix for short-term interests and the compact sketch for long-term preferences. To make training and inference practical, SequenceO1 combines low-rank user representation caching, multi-request user-level batching, pipeline lift, and a fused FlashSA kernel to amortize feature storage, communication, and computation across targets, training instances, and consecutive requests. Production experiments show consistent offline and online gains, while the compact cached sketch retains most of the benefit of directly scaling end-to-end sequence ranking to 100K. These results provide a practical model-system approach to efficient attention, sequence compression, and scalable long-sequence and long-context recommendation systems.

cs.IR↗

arXiv2026

Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation

Automatic fact-checking systems assess the veracity of claims given evidence from relevant documents. Large Language Models (LLMs) have demonstrated strong performance in fact-checking due to their general reasoning capabilities. However, it remains unclear whether they faithfully make use of the evidence provided to reach veracity judgments or rely on parametric knowledge. To investigate this, we introduce Fact-Ablated Evaluation (FAE), a new evaluation framework that iteratively ablates the cited evidence to assess whether LLMs revise their predictions accordingly. Our empirical results show that current off-the-shelf LLMs as fact-checking systems rely more on their parametric knowledge than on the evidence provided. To bridge this gap between prediction accuracy and evidence grounding, we propose REAL (Rigorous Evidence Ablation Learning), a training framework that promotes evidence-dependent verification through counterfactual evidence supervision for the LLM-as-verifier models. Experiments on four fact-checking datasets across different domains demonstrate that models trained with REAL obtain superior evidence-dependent capabilities compared to standard fine-tuned models. Our findings highlight that strong fact-checking performance can still coexist with weak evidence dependency, while REAL encourages veracity predictions to remain more closely tied to the availability of supporting evidence.

cs.CL↗

arXiv2026

Diagnosing LLM Reranker Behavior Under Fixed Evidence Pools

Standard reranking evaluations study how a reranker orders candidates returned by an upstream retriever. This setup couples ranking behavior with retrieval quality, so differences in output cannot be attributed to the ranking policy alone. We introduce a controlled diagnostic for reranking that uses Multi-News clusters as fixed evidence pools. We limit each pool to eight documents and pass identical inputs to all rankers. Within this setup, BM25 and MMR serve as interpretable reference points for lexical matching and diversity optimization. Across 345 clusters, we find that redundancy patterns vary by model: one LLM implicitly diversifies at larger selection budgets, while another increases redundancy. In contrast, LLMs underperform on lexical coverage at small selection budgets. As a result, LLM rankings diverge substantially from both baselines rather than consistently approximating either strategy. By reducing retrieval variance through fixed pools, we interpret these differences more directly as differences in ranking policy. This diagnostic is model agnostic and can be applied to any ranker, including open source systems and proprietary APIs. Our code and processed data for both the Multi-News diagnostic and the complementary TREC-DL evaluation are publicly available at https://github.com/barisarat/llm_reranker_multinews.git.

cs.LG↗

arXiv2026

Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation

Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring factual accuracy. Current detection methods mainly depend on internal signals like uncertainty and self-consistency checks, using the model's pre-trained knowledge to identify unreliable outputs. However, pre-trained knowledge may become outdated and has coverage limitations, especially for specialized or recent information. To address these limitations, retrieval-augmented generation (RAG) has emerged as a promising solution by retrieving relevant evidence at inference time, grounding outputs beyond the model's parametric knowledge. In this paper, we target a critical and practical learning problem RAG-based hallucination detection (RHD), where RAG is employed to enhance hallucination detection by addressing information updating challenges. To address RHD, we propose a novel method Evidence-Aligned Entity Verification (EAEV), which detects entity-level hallucinations by leveraging RAG to align generated entities with retrieved evidence contexts. Specifically, EAEV evaluates entity-evidence alignment through three complementary dimensions and introduces counterfactual stability analysis to ensure robust alignments under evidence perturbations. Experiments across multiple RAG benchmarks demonstrate that EAEV achieves consistent improvements over existing methods with strong generalization capabilities.

cs.AI↗

arXiv2026

Beyond Utility: Evaluating LLM as Recommender

With the rapid development of Large Language Models (LLMs), recent studies employed LLMs as recommenders to provide personalized information services for distinct users. Despite efforts to improve the accuracy of LLM-based recommendation models, relatively little attention is paid to beyond-utility dimensions. Moreover, there are unique evaluation aspects of LLM-based recommendation models, which have been largely ignored. To bridge this gap, we explore four new evaluation dimensions and propose a multidimensional evaluation framework. The new evaluation dimensions include: 1) history length sensitivity, 2) candidate position bias, 3) generation-involved performance, and 4) hallucinations. All four dimensions have the potential to impact performance, but are largely unnecessary for consideration in traditional systems. Using this multidimensional evaluation framework, along with traditional aspects, we evaluate the performance of seven LLM-based recommenders, with three prompting strategies, comparing them with six traditional models on both ranking and re-ranking tasks on four datasets. We find that LLMs excel at handling tasks with prior knowledge and shorter input histories in the ranking setting, and perform better in the re-ranking setting, beating traditional models across multiple dimensions. However, LLMs exhibit substantial candidate position bias issues, and some models hallucinate nonexistent items much more often than others. We intend our evaluation framework and observations to benefit future research on the use of LLMs as recommenders. The code and data are available at https://github.com/JiangDeccc/EvaLLMasRecommender.

cs.IR↗

arXiv2026

Recent Advances and Trends in Research Paper Recommender Systems: A Comprehensive Survey

As the volume of scientific publications grows exponentially, researchers increasingly face difficulties in locating relevant literature. Research Paper Recommender Systems have become vital tools to mitigate this information overload by delivering personalized suggestions. This survey provides a comprehensive analysis of Research Paper Recommender Systems developed between November 2021 and December 2024, building upon prior reviews in the field. It presents an extensive overview of the techniques and approaches employed, the datasets utilized, the evaluation metrics and procedures applied, and the status of both enduring and emerging challenges observed during the research. Unlike prior surveys, this survey goes beyond merely cataloguing techniques and models, providing a thorough examination of how these methods are implemented across different stages of the recommendation process. By furnishing a detailed and structured reference, this work aims to function as a consultative resource for the research community, supporting informed decision-making and guiding future investigations in the advances of effective Research Paper Recommender Systems.

cs.IR↗

arXiv2026

Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval

With the rapid proliferation of multimodal information, Visual Document Retrieval (VDR) has emerged as a critical frontier in bridging the gap between unstructured visually rich data and precise information acquisition. Unlike traditional natural image retrieval, visual documents exhibit unique characteristics defined by dense textual content, intricate layouts, and fine-grained semantic dependencies. This paper surveys the VDR landscape as a retrieval problem in its own right, rather than as the front end of a generation pipeline, and does so specifically through the lens of the Multimodal Large Language Model (MLLM) era. We begin by examining the benchmark landscape, including the recent turn toward reasoning-intensive evaluation, and then dive into the methodological evolution along two orthogonal axes: what a retriever is, spanning multimodal embedding models and reranker models, and how it is deployed, from single-stage retrieval through Retrieval-Augmented Generation (RAG) to Agentic systems. Cutting across both, we analyse the representation--efficiency trade-off that late interaction imposes. We ground these categories in leaderboard evidence on where the empirical frontier actually lies, and close by identifying persistent challenges and outlining promising future directions for multimodal document intelligence.

cs.CL↗

arXiv2026

Adapting Technical-Service LLM Agents with Latent Logic Augmentation, Robust Noise Reduction, and Hybrid Reward Modeling

Technical-service LLM agents are entering production workflows, where value depends on whether engineers adopt generated replies. Service tickets hide decision logic, contain noisy single-reference responses, and make reward evaluation costly, making standard post-training brittle. Existing post-training and LLM-as-a-Judge approaches improve grounding or feedback, but do not jointly model latent decision logic, response diversity, and reward cost. We address this gap by coupling latent logic augmentation, robust noise reduction, and hybrid reward modeling. The framework augments supervised fine-tuning data with Planning-Aware Trajectory Modeling and Reasoning Augmentation, builds dual-filtered Multiple Ground Truths, and trains the policy with a hybrid reward that combines a Reranker with an LLM-as-a-Judge. On real Cloud technical-service tasks, the adapted Qwen3-4B achieves the highest Multi-ECS (0.441), lower reward cost, and the highest production adoption rate (46.63%).

cs.LG↗

arXiv2026

Enhancing Healthcare Search Intent Recognition with Query Representation Learning and Session Context

Classifying the intent behind healthcare search queries is crucial for improving the delivery of online healthcare information. The intricate nature of medical search queries, coupled with the limited availability of high-quality labeled data, presents substantial challenges for developing efficient classification models. Previous studies have exploited user interaction data, such as user clicks from search logs and employed pairwise loss functions to model co-click behavior for query representation learning. However, many health queries could have multiple intents, resulting in ambiguous or divergent click behavior. Furthermore, learning the single most popular intent of queries as inferred from global statistics based on the aggregate behavior of different users could potentially lead to disparity and performance drop when classifying the query intent within specific search sessions. To address these limitations, our work improves the query representation learning by aggregating similar queries via clustering, and introducing a novel loss function designed to capture the multifaceted nature of health search queries, resulting in a more scalable and accurate learning procedure. Furthermore, we quantify the ambiguity of health queries and the misalignment between global search intents and those discerned from individual sessions, by introducing the concordance rate (CR) score, and demonstrate a simple and effective method for incorporating our learned query representation into contextual, session-based search intent classification. Our extensive experimental results and analysis on two real-world search log datasets, i.e., a Health Search (HS) dataset and the publicly available TripClick dataset, demonstrate that our approach not only improves the intrinsic clustering metrics for query representation learning but also enhances accuracy for subsequent search intent classification tasks.

cs.IR↗

arXiv2026

Crowd-OM: Crowdsourcing for Ontology Matching Validation

Recent advances in large language models (LLMs) pose new challenges for ontology matching (OM). While OM systems built on LLMs have shown remarkable capabilities in discovering more matching candidates, traditional OM validation that relies on domain experts has become overwhelming. Although crowdsourcing can expose OM validation to large online communities, bias and errors from diverse annotators can reduce the quality of crowdsourcing for OM validation. In this study, we explore the use of crowdsourcing for OM validation and introduce a novel quality assurance crowdsourcing system called Crowd-OM. In order to ensure the quality of crowdsourcing for OM validation, we propose three domain-specific mechanisms, namely differential trustworthiness, coherence pre-filling, and time-dependent modelling. Crowd-OM can be integrated with existing OM systems to enable human-in-the-loop validation. The evaluation shows its effectiveness in handling various annotators and different annotation scenarios. We discuss two real-world use cases and current limitations for improvement.

cs.IR↗

arXiv2026

Bayesian Rational Search Engine User

A user faces a list returned by a search system, ordered by a noisy proxy for relevance, and decides whether to pay a fixed cost to inspect another item or stop with the best she has uncovered. She does not enter the page knowing how good its items are, so each inspection both produces a candidate item and refines her belief about the page's underlying quality. We show that the optimal policy is a standout rule: the user stops once her best find is sufficiently good relative to what she expects from the page, with the required margin changing with depth. The resulting dynamics collapse to a one-dimensional Markov chain, which yields the full distribution of inspection depth through a closed-form recursion. The model uncovers three hidden mechanisms that explain why users stop: trust, commit, and cut-losses. It also yields a rich set of testable implications. The same Bayesian-rational view turns inspection depth into a learning-to-rank likelihood: an observed depth restricts the latent relevance path to a polyhedron of survival inequalities, while a conversion further identifies the terminal winner. Simulations show that the resulting estimator recovers relevance under correct specification and improves ranking when restricted to the features available to the incumbent ranker. Applied to public Baidu search logs, the inspection depth likelihood produces rankings that align more closely with expert relevance judgments than click-trained alternatives.

cs.IR↗

arXiv2026

Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval

Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interaction, but dense image-side tokens make storage and scoring expensive. Existing token compression methods reduce this cost, yet they can remove or collapse object- and region-level evidence that future query tokens may need to select. We propose SaMer, an object-aware token merging framework that compresses image-side post-projector tokens into $K$ representative centroids while preserving the original late-interaction interface. SaMer uses object annotations only during training as a merge prior to discourage cross-instance mixing, requires no ground-truth bounding boxes or detectors at inference time, and adapts only the shared projection layer with frozen vision and language backbones. With $K=64$, SaMer removes more than 93% of image-side tokens and reduces ColPali storage by $16.09\times$, while improving R@1 on Flickr30K and MSCOCO. These gains arise because object-aware merging preserves query-selectable object evidence that pruning or feature-only pooling can remove or collapse. SaMer also outperforms compression baselines and shows stronger phrase-level grounding, suggesting that efficient multi-vector retrieval depends not only on reducing token count, but on preserving the evidence future query tokens need to select.

cs.IR↗

arXiv2026

Decoupled Temporal Encoding for Generative Recommendation

Positional encoding is a fundamental component of Transformer-based generative recommendation models, where user histories are modeled as autoregressive item sequences. Most positional encoding methods are inherited from natural language processing and mainly represent discrete item order. However, recommendation sequences go beyond ordered lists, as timestamps and temporal effects also shape item relations. Our work is motivated by a real-world food delivery and instant retail recommendation system, where user behavior exhibits multi-level temporal regularities, including recency effects, meal-time peaks, weekday-weekend shifts, and promotion-driven traffic bursts. Existing methods partially address this issue through timestamp features, interval embeddings, decay functions, or attention biases, but they usually inject heterogeneous temporal signals through a unified representation or a single modeling pathway, making it difficult to distinguish broad temporal dynamics from local order cues. To address this limitation, we propose Decoupled Temporal Encoding (DTE), a lightweight framework for generative recommendation. DTE separates temporal dynamics from order information through two complementary modules: a personalized macro-temporal module that injects compact temporal primitives into item embeddings, and a time-gated micro-sequential module that introduces relative-order bias only when interactions are temporally dense. DTE is also parameter-efficient and deployment-friendly, allowing easy integration into existing systems.

cs.IR↗

arXiv2026

A Storage-Retrieval Gap in Parametric Knowledge Graph Memory

Graph retrieval-augmented generation places retrieved subgraphs into the model's context window at query time, paying a recurring token cost and exposing source data on every call. We study an alternative: compiling a knowledge graph offline into a bank of LoRA adapters, one per entity, that serve as a parametric knowledge layer queried by injecting weights rather than text, at zero query-time context cost. On the MetaQA dataset, we find that subgraph-trained adapters encode context-free factual knowledge that generalizes to unseen questions: on single-valued relations the adapter gains $+0.243$ exact-match score over a base model that is nearly blind closed-book ($0.007$), and only the correct adapter recovers this knowledge (an oracle gap of $+0.283$ over the base model). However, the stored knowledge is not recoverable by similarity: given a query with no subgraph, embedding-based and weight-space geometry retrieval both perform at chance, because a semantically neighbouring entity's adapter does not contain the answer - knowledge is stored locally and does not transfer. Weight geometry correlates with subgraph semantics ($ρ= +0.329$) but not with functional retrievability. We quantify the byte and context-token costs against graph retrieval-augmented generation and discuss deployment implications. Our results establish that parametric knowledge graph memory is feasible for storing knowledge, and identify selecting and composing the right adapters by a mechanism other than semantic similarity as the central open problem - motivating a learned, query-conditioned composition mechanism.

cs.LG↗

arXiv2026

Local-to-Global Sentence-Level Graph Reranking for Scientific Synthesis

Retrieval-augmented scientific synthesis aims to answer complex research questions by integrating information from multiple papers into comprehensive and well-grounded responses. Since the generator can only synthesize the information selected and organized by the reranker, the quality of the generated synthesis depends critically on the reranked results. However, most rerankers operate at the passage level, which leaves key methodological, empirical, and comparative information buried in long and flat contexts, weakening the grounding of generated claims. Moreover, existing rerankers mainly rely on independent query-candidate scoring which overlooks complementary, contextual, and contrasting relations across scientific candidates, limiting information coverage and the comprehensiveness of the resulting synthesis. To address these limitations, we propose LoG-Reranker, a local-to-global sentence-level graph reranking framework for scientific synthesis. LoG-Reranker performs role-aware local scoring to identify fine-grained, query-relevant sentences and then models their relations on a sentence graph across the candidate set to globally refine sentence rankings. Top-ranked sentences and their connected neighbors are organized into a structured input context for generator to produce more grounded and comprehensive synthesis. Extensive experiments on scientific synthesis and reranking benchmarks show that LoG-Reranker consistently outperforms competitive rerankers, yielding more reliable rankings and improving the quality of generated synthesis.

cs.IR↗

arXiv2026

Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers

Customer-service QA in an AI contact center (AICC) runs under deployment constraints that benchmark QA misses: tight voice-hotline latency and a high cost for unsupported or wrong automatic answers. We deploy a system that answers only from a closed set of verified QA units: it returns a retrieved unit verbatim, or routes to clarify, abstain, or handoff. The index is enriched offline by staged linguistic seeding (SLS): a human authors a per-unit world-grounded slot recipe, gpt-4.1-mini renders it into variants, and a light human gate filters them. One methodology is reused across both domains, so inference stays a single retrieval pass with no query-time generation. On held-out query variants from two industrial domains, SLS lifts hybrid R@1 to 0.881/0.930 (+0.27/+0.34), with gains across all five retrievers tested. At the same gpt-4.1-mini generation budget, SLS beats doc2query by +0.20/+0.32, while cross-provenance evaluation provides additional evidence of transfer across generated-query distributions. Verified-unit answering also removes free-form generation's unsupported-content surface (7-13% versus approximately 0%). We report this as an application study, including negative results.

cs.CL↗

arXiv2026

FunnelAudit: Responsibility Auditing in Multi-Route Recommender Systems

Multi-route recommender systems combine retrieval, allocation, fusion, and ranking, making individual inclusions and exclusions difficult to audit. Route overlap can hide effects from one-at-a-time ablations, while freezing downstream stages produces counterfactuals inconsistent with serving behavior. We introduce FunnelAudit, an executable framework for incident-level responsibility auditing. An accountability contract specifies the disputed Top-K event, controls and owners, permitted reference actions, and replay semantics. FunnelAudit evaluates every permitted control configuration and applies graded actual responsibility to find the smallest outcome-preserving contingency that makes each control pivotal. Its certificate records the contingency and paired serving executions needed to verify the judgment. We instantiate the framework in two-stage, nine-route funnels using fixed union, weighted quota allocation, or weighted reciprocal-rank fusion, followed by SASRec ranking. Across 258,809 user-target incidents from three real interaction datasets, 4.24-16.24% admit a responsible control. Among responsible incident-control pairs, 92.55-99.64% require a nonempty contingency, so single-control ablation recovers only 0.36-7.45%. Policies differing in factual outcomes on only 0.31-2.39% of incidents yield 21.44-54.05% Jaccard distance between responsible-route sets on matched exclusions. Independent replay reproduces all 9,121,792 checked target-world outcomes; exhaustive search and a generic mixed-integer linear program agree with every sampled judgment. These findings demonstrate the importance of explicit serving semantics and checkable witnesses for recommender accountability.

cs.IR↗

arXiv2026

Tracing Query Expansion Effects through Sparse Autoencoder Features

Query expansion (QE) is a critical technique in information retrieval that enriches underspecified queries with additional textual context. However, its effect is often unreliable in modern dense retrieval, especially for strong off-the-shelf retrievers without retraining. Existing studies mainly examine expansion quality, semantic drift, or retrieval outcomes, but rarely explain how QE changes dense retrievers internally. In this work, we trace QE effects through sparse autoencoder (SAE) features. Using paired original and expanded queries, we decompose layer-wise retriever representations into sparse latent activations, identify QE-related latents from expansion-induced activation shifts, and interpret them with natural-language descriptions and retrieval cases. Our analysis shows that effective QE induces layer-concentrated changes in sparse latents aligned with retrieval intent and entity attributes, rather than only perturbing final query embeddings. SAE-based activation steering further validates these latents improve retrieval more consistently than random interventions or vanilla QE across four benchmarks, suggesting that SAEs can explain QE effects and offer a lightweight option for precise retrieval behavior modulation without query rewriting or retriever fine-tuning.

cs.IR↗