Deployable multilingual rerankers must generalize across languages, domains, and target ranking tasks while remaining efficient enough for second-stage reranking. However, adapting them to new target distributions typically requires extensive task-specific relevance annotations, which are costly to obtain. We present Querit-Reranker, a family of multilingual cross-encoder rerankers trained with a data-centric pipeline for label-efficient adaptation. We instantiate it as Querit-Reranker-A0.4B, initialized from an in-house MoE backbone with 0.4B activated parameters, and Querit-Reranker-4B, initialized from Qwen3-Embedding-4B. Our pipeline first learns general relevance modeling from large-scale ranking-oriented data, then adapts to target distributions through synthetic-query mining with teacher scores as continuous soft labels. To consolidate complementary task-adapted strengths, we further merge checkpoints via spherical linear interpolation, obtaining a single deployable model without runtime ensembling overhead. Using Qwen3-Embedding-0.6B as the shared first-stage retriever, Querit-Reranker-A0.4B improves average nDCG@10 from 54.11 to 59.28 on BEIR and from 59.87 to 67.70 on MIRACL. On MTEB Multilingual v2 Reranking, it also substantially outperforms larger embedding-based baselines, while Querit-Reranker-4B further achieves state-of-the-art performance among publicly available models. We release both models on Hugging Face.

Recent advances in neural information retrieval models have significantly enhanced these models’ effectiveness across information retrieval tasks. The robustness of these models, which is essential for ensuring their reliability in practice, has also garnered significant attention. With a wide array of research on robust information retrieval being published, we believe it is the opportune moment to consolidate the current status, glean insights from existing methodologies, and lay the groundwork for future development. Robustness of information retrieval is a multifaceted concept and we emphasize the importance of robustness against performance variance, out-of-distribution scenarios, and adversarial attacks. With a focus on out-of-distribution and adversarial robustness, we dissect robustness solutions for dense retrieval models and neural ranking models, respectively, recognizing them as pivotal components of the neural information retrieval pipeline. We provide an in-depth discussion of methods, datasets, and evaluation metrics, shedding light on challenges and future directions in the era of large language models. To accompany this survey, we release three additional resources: (1) a curated list of publications related to robust information retrieval, (2) a tutorial based on this survey, and (3) a heterogeneous benchmark for robust information retrieval, BestIR, that collects all known datasets for evaluating information retrieval systems for robustness. We hope that this study provides useful clues for future research on the robustness of information retrieval models and helps to develop trustworthy IR systems.

As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track social relations, reason over norms, and adapt behavior under context. This report presents ZenGen, an integrated framework for measuring, internalizing, and grounding social intelligence. For measurement, we introduce SoMBench, a psychology-grounded benchmark spanning 3 primary dimensions, 17 secondary dimensions, and 71 task paradigms. It controls question format, narrative perspective, and context length across 284 shared scenarios and 3,481 expert-verified instances. Evaluation of 20 representative LLMs reveals substantial headroom: the best model achieves only 72.08

While neural ranking models (NRMs) have achieved state-of-the-art performance in information retrieval, they remain highly vulnerable to imperceptible adversarial perturbations. Existing defenses are predominantly data-centric, exemplified by adversarial training, which requires constructing large collections of adversarial examples. By treating NRMs as black boxes and indiscriminately optimizing all model parameters, these methods incur substantial computational cost and often degrade performance on clean data due to overfitting. In this paper, we advocate that adversarial vulnerability is not uniformly distributed across model parameters, but instead originates from specific internal units. We propose a paradigm shift toward a model-centric defense that addresses vulnerability at its architectural source, without requiring costly retraining or adversarial data generation. Specifically, we introduce Search in the Model, a novel training-free framework that performs fine-grained identification and rectification of vulnerable neurons directly within the model. By formulating neuron identification as a ranking problem, we develop a maximum marginal vulnerability criterion to precisely locate the top- K neurons most responsible for model vulnerability, and apply targeted neuronal inverse perturbation to correct them. Extensive experiments on MS MARCO and TREC 19 show that our approach outperforms state-of-the-art baselines in both defense efficiency and robustness to seen and unseen attacks, while preserving strong performance on clean data.

Open-source intelligence analysis plays an increasingly important role in supporting complex decision-making. However, traditional intelligence analysis processes are inefficient due to challenges such as the complexity and variability of tasks, the difficulty of processing multi-source heterogeneous information, and the reliance on expert experience for deep reasoning. To address these issues, this paper proposes a deep research agent framework for intelligence analysis. This framework simulates a human intelligence analysis team, constructing a system led by a "Task Planning Agent" and coordinated by specialized sub-agents, including the "Information Collection Agent," "Information Identification Agent," and "Insight Generation Agent." The framework aims to automate the entire process, from task decomposition to the production of complete intelligence reports. To validate the effectiveness of the framework, we constructed an evaluation dataset for complex intelligence tasks. The results show that the frameworksignificantly outperforms baseline models in terms of generated report quality (RACT), but still has room for improvement in terms of citation performance in web retrieval (FACT).

Retrieval-augmented generation (RAG) enhances large language model (LLM) reasoning by retrieving external documents, but also opens up new attack surfaces. We study knowledge-base poisoning attacks in RAG, where an attacker injects malicious content into the retrieval corpus, which is then naturally surfaced by the retriever and consumed by the LLM during reasoning. Unlike prior work that floods the corpus with poisoned documents, we propose AdversarialCoT, a query-specific attack that poisons only a single document in the corpus. AdversarialCoT first extracts the target LLM's reasoning framework to guide the construction of an initial adversarial chain-of-thought (CoT). The adversarial document is iteratively refined through interactions with the LLM, progressively exposing and exploiting critical reasoning vulnerabilities. Experiments on benchmark LLMs show that a single adversarial document can significantly degrade reasoning accuracy, revealing subtle yet impactful weaknesses. This study exposes security risks in RAG systems and provides actionable insights for designing more robust LLM reasoning pipelines.

Decoder-only large language models (LLMs) are increasingly replacing BERT-style architectures as the backbone for dense retrieval, achieving substantial performance gains and broad adoption. However, the robustness of these LLM-based retrievers remains underexplored. In this paper, we present the first systematic study of the robustness of state-of-the-art open-source LLM-based dense retrievers from two complementary perspectives: generalizability and stability. For generalizability, we evaluate retrieval effectiveness across four benchmarks spanning 30 datasets, using linear mixed-effects models to estimate marginal mean performance and disentangle intrinsic model capability from dataset heterogeneity. Our analysis reveals that while instruction-tuned models generally excel, those optimized for complex reasoning often suffer a “specialization tax,” exhibiting limited generalizability in broader contexts. For stability, we assess model resilience against both unintentional query variations (e.g., paraphrasing, typos) and malicious adversarial attacks (e.g., corpus poisoning). We find that LLM-based retrievers show improved robustness against typos and corpus poisoning compared to encoder-only baselines, yet remain vulnerable to semantic perturbations like synonymizing. Further analysis shows that embedding geometry (e.g., angular uniformity) provides predictive signals for lexical stability and suggests that scaling model size generally improves robustness. These findings inform future robustness-aware retriever design and principled benchmarking. Our code is publicly available at https://github.com/liyongkang123/Robust_LLM_Retriever_Eval.

Retrieval-augmented generation (RAG) has emerged as a promising paradigm for mitigating hallucinations in large language models (LLMs).However, the intrinsic heterogeneity between the retriever and the generator often leads to a mismatch between retrieved evidence and generation needs, hindering effective coordination.We argue that competition between discriminative retrieval and generative modeling can more effectively expose their mutual weaknesses and induce deeper interaction. Motivated by this insight, we propose CARL (Co-opetition AdveRsarial Learning), a framework that formulates retriever–generator training in RAG as a minimax game. In this game, the retriever is optimized to retrieve both useful and adversarially useless documents to challenge the generator, while the generator learns to identify useful evidence and remain robust to misleading retrievals to produce accurate answers.Experiments on seven benchmark datasets demonstrate that CARL consistently improves RAG performance, validating the effectiveness of adversarial co-opetition in enhancing retriever–generator synergy.

Knowledge-intensive language tasks (KILTs) typically require retrieving relevant documents from trustworthy corpora, e.g., Wikipedia, to produce specific answers. Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, was proposed and reached new state-of-the-art retrieval performance. However, most existing research on KILTs, including CorpusBrain, has predominantly focused on a static document collection, overlooking the dynamic nature of real-world scenarios, where new documents are continuously being incorporated into the source corpus. To address this gap, it is crucial to explore the capability of retrieval models to effectively handle the dynamic retrieval scenario inherent in KILTs. In this work, we first introduce the continual document learning (CDL) task for KILTs and build a novel benchmark dataset named KILT++ based on the original KILT dataset for evaluation. Then, we conduct a comprehensive study over the use of pre-trained CorpusBrain on KILT++. Unlike the promising results in the stationary scenario, CorpusBrain is prone to catastrophic forgetting in the dynamic scenario, hence hampering the retrieval performance. To alleviate this issue, we propose CorpusBrain++, a continual generative pre-training framework. Empirical results demonstrate the significant effectiveness and remarkable efficiency of CorpusBrain++ in comparison to both traditional and generative IR methods.

The advancement of large language models (LLMs) has significantly boosted the performance of complex long-form question answering tasks. However, one prominent issue of LLMs is the generated "hallucination" responses that are not factual. Consequently, attribution for each claim in responses becomes a common solution to improve the factuality and verifiability. Existing researches mainly focus on how to provide accurate citations for the response, which largely overlook the importance of identifying the claims or statements for each response. To bridge this gap, we introduce a new claim decomposition benchmark, which requires building system that can identify atomic and checkworthy claims for LLM responses. Specifically, we present the Chinese Atomic Claim Decomposition Dataset (CACDD), which builds on the WebCPM dataset with additional expert annotations to ensure high data quality. The CACDD encompasses a collection of 500 human-annotated question-answer pairs, including a total of 4956 atomic claims. We further propose a new pipeline for human annotation and describe the challenges of this task. In addition, we provide experiment results on zero-shot, few-shot and fine-tuned LLMs as baselines. The results show that the claim decomposition is highly challenging and requires further explorations. All code and data are publicly available (https://github.com/FBzzh/CACDD).

Multi-behavior recommendation (MBR) has garnered growing attention recently due to its ability to mitigate the sparsity issue by inferring user preferences from various auxiliary behaviors to improve predictions for the target behavior. Although existing research on MBR has yielded impressive results, it still faces two major limitations. First, previous methods mainly focus on modeling fine-grained interaction information between users and items under each behavior, which may suffer from sparsity issue. Second, existing models usually concentrate on exploiting dependencies between two consecutive behaviors, leaving intra-and inter-behavior consistency largely unexplored. To this end, we propose a novel approach named Consistent Multi-Granularity Cascading Graph Convolution Network for Multi-Behavior Recommendation (CMC-GCN). To be specific, we first explore both fine-and coarse-grained correlations among users or items of each behavior by simultaneously modeling the behavior-specific interaction graph and its corresponding hypergraph in a cascaded manner. Then, we propose a behavior consistency-guided alignment strategy that preserves consistent representations between the interaction graph and its associated hypergraph for each behavior, while also maintaining representation consistency across different behaviors. Extensive experiments and analyses on four real-world benchmark datasets demonstrate that our proposed approach is consistently superior to previous state-of-the-art methods due to its capability to effectively attenuate the sparsity issue as well as keep both intra-and inter-behavior consistencies. The code is available at https://github.com/marqu22/CMCGCN.git.

Robustness and Effectiveness are critical aspects of developing dense retrieval models for real-world applications. It is known that there is a trade-off between the two. Recent work has addressed scaling laws of effectiveness in dense retrieval, revealing a power-law relationship between effectiveness and the size of models and data. Does robustness follow scaling laws too? If so, can scaling improve both robustness and effectiveness together, or do they remain locked in a trade-off? To answer these questions, we conduct a comprehensive experimental study. We find that:(i) Robustness, including out-of-distribution and adversarial robustness, also follows a scaling law.(ii) Robustness and effectiveness exhibit different scaling patterns, leading to significant resource costs when jointly improving both. Given these findings, we shift to the third factor that affects model performance, namely the optimization strategy, beyond the model size and data size. We find that: (i) By fitting different optimization strategies, the joint performance of robustness and effectiveness traces out a Pareto frontier. (ii) When the optimization strategy strays from Pareto efficiency, the joint performance scales in a sub-optimal direction. (iii) By adjusting the optimization weights to fit the Pareto efficiency, we can achieve Pareto training, where the scaling of joint performance becomes most efficient. Even without requiring additional resources, Pareto training is comparable to the performance of scaling resources several times under optimization strategies that overly prioritize either robustness or effectiveness. Finally, we demonstrate that our findings can help deploy dense retrieval models in real-world applications that scale efficiently and are balanced for robustness and effectiveness.

The first-stage retrieval aims to retrieve a subset of candidate documents from a huge collection both effectively and efficiently. Since various matching patterns can exist between queries and relevant documents, previous work tries to combine multiple retrieval models to find as many relevant results as possible. The constructed ensembles, whether learned independently or jointly, do not care which component model is more suitable to an instance during training. Thus, they cannot fully exploit the capabilities of different types of retrieval models in identifying diverse relevance patterns. Motivated by this observation, in this paper, we propose a Mixture-of-Experts (MoE) model consisting of representative matching experts and a novel competitive learning mechanism to let the experts develop and enhance their expertise during training. Specifically, our MoE model shares the bottom layers to learn common semantic representations and uses differently structured upper layers to represent various types of retrieval experts. Our competitive learning mechanism has two stages: (1) a standardized learning stage to train the experts equally to develop their capabilities to conduct relevance matching; (2) a specialized learning stage where the experts compete with each other on every training instance and get rewards and updates according to their performance to enhance their expertise on certain types of samples. Experimental results on three retrieval benchmark datasets show that our method significantly outperforms the state-of-the-art baselines.

Retrieval-augmented generation (RAG) appears as a promising method to alleviate the "hallucination" problem in large language models (LLMs), since it can incorporate external traceable resources for response generation. The essence of RAG in combating the hallucination issue lies in accurately attributing claims in responses to the corresponding retrieved documents. However, most of existing works focus on improving the quality of generated responses from the LLM, while largely overlooked its ability to attribute sources accurately. In this study, we conduct a systematic analysis about the capabilities of LLMs in generating citations within response generation, and further introduce a novel method to enhance their citation generation abilities. Specifically, we evaluate both the correctness and citation quality for seven widely-used LLMs on two benchmark datasets. Meanwhile, we introduce new citation evaluation metrics to eliminate the over-penalization of unnecessary and excessive citations in existing metrics. Furthermore, we propose a Generate-then-Refine method that completes relevant citations and removes irrelevant ones without altering the response text. The results on WebGLM-QA, ASQA and ELI5 datasets show that our method substantially improves the quality of citations in responses generated by LLMs.

Retrieval-Augmented Generation (RAG) has emerged as a crucial approach for enhancing the responses of large language models (LLMs) with external knowledge sources. Despite the impressive performance in complex question-answering tasks, RAG still struggles with hallucinations. Attributing RAG-generated content through in-line citations has demonstrated potential in reducing hallucinations and facilitating human verification. Existing citation generation methods primarily rely on either fine-tuning the generator or employing post-processing approaches for citation matching. However, the former approach demands substantial annotated data and computational resources, while the latter often encounters difficulties in managing multiple citations and frequently produces suboptimal results. In this paper, we introduce a novel framework, called VeriCite, designed to rigorously validate supporting evidence and enhance answer attribution. Specifically, VeriCite breaks down into a three-stage generation: 1) The initial answer generation first generates a response based on all available contexts and has its claims verified through the NLI model; 2) the supporting evidence selection assesses the utility of each document and extracts useful supporting evidences; 3) the final answer refinement integrates the initial response and collected evidences to produce the final, refined answer.We conduct experiments across five open-source LLMs and four datasets, demonstrating that VeriCite can significantly improve citation quality while maintaining the correctness of the answers.

Retrieval-augmented generation (RAG) systems can effectively mitigate the hallucination problem of large language models (LLMs),but they also possess inherent vulnerabilities. Identifying these weaknesses before the large-scale real-world deployment of RAG systems is of great importance, as it lays the foundation for building more secure and robust RAG systems in the future. Existing adversarial attack methods typically exploit knowledge base poisoning to probe the vulnerabilities of RAG systems, which can effectively deceive standard RAG models. However, with the rapid advancement of deep reasoning capabilities in modern LLMs, previous approaches that merely inject incorrect knowledge are inadequate when attacking RAG systems equipped with deep reasoning abilities. Inspired by the deep thinking capabilities of LLMs, this paper extracts reasoning process templates from R1-based RAG systems, uses these templates to wrap erroneous knowledge into adversarial documents, and injects them into the knowledge base to attack RAG systems. The key idea of our approach is that adversarial documents, by simulating the chain-of-thought patterns aligned with the model's training signals, may be misinterpreted by the model as authentic historical reasoning processes, thus increasing their likelihood of being referenced. Experiments conducted on the MS MARCO passage ranking dataset demonstrate the effectiveness of our proposed method.

Generative retrieval (GR) has emerged as a new paradigm in neural information retrieval, offering an alternative to dense retrieval (DR) by directly generating identifiers of relevant documents. In this paper, we theoretically and empirically investigate how GR fundamentally diverges from DR in both learning objectives and representational capacity. GR performs globally normalized maximum-likelihood optimization and encodes corpus and relevance information directly in the model parameters, whereas DR adopts locally normalized objectives and represents the corpus with external embeddings before computing similarity via a bilinear interaction. Our analysis suggests that, under scaling, GR can overcome the inherent limitations of DR, yielding two major benefits. First, with larger corpora, GR avoids the sharp performance degradation caused by the optimization drift induced by DR's local normalization. Second, with larger models, GR's representational capacity scales with parameter size, unconstrained by the global low-rank structure that limits DR. We validate these theoretical insights through controlled experiments on the Natural Questions and MS MARCO datasets, across varying negative sampling strategies, embedding dimensions, and model scales. But despite its theoretical advantages, GR does not universally outperform DR in practice. We outline directions to bridge the gap between GR's theoretical potential and practical performance, providing guidance for future research in scalable and robust generative retrieval.

Entity linking (EL) is a challenging task as it typically requires matching an ambiguous entity mention with its corresponding entity in a knowledge base (KB). The mainstream studies focus on learning and evaluating linking models on the same corpus and obtained significant performance achievement, however, they often overlook the generalization ability to out-of-domain corpus, which is more realistic yet much more challenging. To address this issue, we introduce a novel neural-symbolic model for entity linking, which is inspired by the symbol-manipulation mechanism in human brains. Specifically, we abstract diverse features into unified variables, then combine them using neural operators to capture diverse relevance requirements, and finally aggregate relevance scores through voting. We conduct experiments on eleven benchmark datasets with different types of text, and the results show that our method outperforms nearly all baselines. Notably, the best performance of our method on seven out-of-domain datasets highlights its generalization ability.