Researcher profile

Qingyao Ai

Qingyao Ai contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Information Retrieval Artificial Intelligence Computation and Language Machine Learning

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

16works

0followers

4topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

A Causal Information-Flow Framework for Unbiased Learning-to-Rank

In web search and recommendation systems, user clicks are widely used to train ranking models. However, click data is heavily biased, i.e., users tend to click higher-ranked items (position bias), choose only what was shown to them (selection bias), and trust top results more (trust bias). Without explicitly modeling these biases, the true relevance of ranked items cannot be correctly learned from clicks. Existing Unbiased Learning-to-Rank (ULTR) methods mainly correct position bias and rely on propensity estimation, but they cannot measure remaining bias, provide risk guarantees, or jointly handle multiple bias sources. To overcome these challenges, this paper introduces a novel causal learning-based ranking framework that extends ULTR by combining Structural Causal Models (SCMs) with information-theoretic tools. SCMs specify how clicks are generated and help identify the true relevance signal from click data, while conditional mutual information, measures how much bias leaks into the learned relevance estimates. We use this leakage measure to define a rigorous notion of disentanglement and include it as a regularizer during model training to reduce bias. In addition, we incorporate a causal inference estimator, i.e., doubly robust estimator, to ensure more reliable risk estimation. Experiments on standard Learning-to-Rank benchmarks show that our method consistently reduces measured bias leakage and improves ranking performance, especially in realistic scenarios where multiple biases-such as position and trust bias-interact strongly.

preprint2026arXiv

Decoupling Knowledge and Task Subspaces for Composable Parametric Retrieval Augmented Generation

Parametric Retrieval-Augmented Generation (PRAG) encodes external documents into lightweight parameter modules that can be retrieved and merged at inference time, offering a promising alternative to in-context retrieval augmentation. Despite its potential, many PRAG implementations train document adapters with task-supervised objectives, which may cause each adapter to encode both document-specific facts and reusable task-solving behavior. This entanglement may make adapter composition less reliable: when multiple adapters are merged at inference time, their overlapping task behaviors can accumulate together with document-specific updates, potentially making the merged adapter less stable and less focused on the intended document knowledge. To examine this issue, we explore Orthogonal Subspace Decomposition (OSD), an adapter-training setup that separates reusable task behavior from document-specific knowledge adapters. Concretely, we first train a Task LoRA to capture reusable task behavior, and then train document LoRAs to encode document-specific knowledge in a orthogonal subspace. This setup provides a controlled way to examine how orthogonalizing task and document LoRA updates affects adapter composition in multi-document PRAG. Experiments across multiple knowledge-intensive tasks and model scales suggest that this orthogonalization strategy can improve compositional robustness in parametric RAG, especially when multiple document adapters are merged.

preprint2026arXiv

Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization

Automating the drafting of judgment documents is pivotal to judicial efficiency, yet it remains challenging due to the dual requirements of comprehensive retrieval of legal information and rigorous logical reasoning. Existing approaches, typically relying on standard Retrieval-Augmented Generation and Supervised Fine-Tuning, often suffer from insufficient evidence recall, hallucinated statutory references, and logically flawed legal reasoning. To bridge this gap, we propose Judge-R1, a unified framework designed to enhance LLM-based judgment document generation by jointly improving legal information collection and judgment document generation. First, we introduce Agentic Legal Information Collection, which employs a dynamic planning agent to retrieve precise statutes and precedents from multiple sources. Second, we implement Rubric-Guided Optimization, a reinforcement learning phase utilizing Group Relative Policy Optimization (GRPO) with a comprehensive legal reward function to enforce adherence to judicial standards and reasoning logic. Extensive experiments on the JuDGE benchmark demonstrate that Judge-R1 significantly outperforms state-of-the-art baselines in both legal accuracy and generation quality.

preprint2026arXiv

How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study

While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by which humans can successfully recognize or be misled by these hallucinations remain unclear. To address this problem, this paper explores humans' neural dynamics to characterize how the brain processes hallucinated content. We record EEG signals from 27 participants while they are performing a verification task to judge the correctness of image descriptions generated by a multi-modal large language model (MLLM). Based on an averaged event-related potential (ERP) study, we reveal that multiple cognitive processes, e.g., semantic integration, inferential processing, memory retrieval, and cognitive load, exhibit distinct patterns when humans process hallucinated versus non-hallucinated content. Notably, neural responses to hallucinations that were misjudged versus correctly judged by human participants showed significant differences. This indicates that misjudged AI-generated hallucinations failed to trigger the standard neurocognitive fact verification pathway.

preprint2024arXiv

Caseformer: Pre-training for Legal Case Retrieval Based on Inter-Case Distinctions

Legal case retrieval aims to help legal workers find relevant cases related to their cases at hand, which is important for the guarantee of fairness and justice in legal judgments. While recent advances in neural retrieval methods have significantly improved the performance of open-domain retrieval tasks (e.g., Web search), their advantages have not been observed in legal case retrieval due to their thirst for annotated data. As annotating large-scale training data in legal domains is prohibitive due to the need for domain expertise, traditional search techniques based on lexical matching such as TF-IDF, BM25, and Query Likelihood are still prevalent in legal case retrieval systems. While previous studies have designed several pre-training methods for IR models in open-domain tasks, these methods are usually suboptimal in legal case retrieval because they cannot understand and capture the key knowledge and data structures in the legal corpus. To this end, we propose a novel pre-training framework named Caseformer that enables the pre-trained models to learn legal knowledge and domain-specific relevance information in legal case retrieval without any human-labeled data. Through three unsupervised learning tasks, Caseformer is able to capture the special language, document structure, and relevance patterns of legal case documents, making it a strong backbone for downstream legal case retrieval tasks. Experimental results show that our model has achieved state-of-the-art performance in both zero-shot and full-data fine-tuning settings. Also, experiments on both Chinese and English legal datasets demonstrate that the effectiveness of Caseformer is language-independent in legal case retrieval.

preprint2024arXiv

Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval

With the development of deep learning and natural language processing techniques, pre-trained language models have been widely used to solve information retrieval (IR) problems. Benefiting from the pre-training and fine-tuning paradigm, these models achieve state-of-the-art performance. In previous works, plain texts in Wikipedia have been widely used in the pre-training stage. However, the rich structured information in Wikipedia, such as the titles, abstracts, hierarchical heading (multi-level title) structure, relationship between articles, references, hyperlink structures, and the writing organizations, has not been fully explored. In this paper, we devise four pre-training objectives tailored for IR tasks based on the structured knowledge of Wikipedia. Compared to existing pre-training methods, our approach can better capture the semantic knowledge in the training corpus by leveraging the human-edited structured data from Wikipedia. Experimental results on multiple IR benchmark datasets show the superior performance of our model in both zero-shot and fine-tuning settings compared to existing strong retrieval baselines. Besides, experimental results in biomedical and legal domains demonstrate that our approach achieves better performance in vertical domains compared to previous models, especially in scenarios where long text similarity matching is needed.

preprint2022arXiv

Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval

Recent advance in Dense Retrieval (DR) techniques has significantly improved the effectiveness of first-stage retrieval. Trained with large-scale supervised data, DR models can encode queries and documents into a low-dimensional dense space and conduct effective semantic matching. However, previous studies have shown that the effectiveness of DR models would drop by a large margin when the trained DR models are adopted in a target domain that is different from the domain of the labeled data. One of the possible reasons is that the DR model has never seen the target corpus and thus might be incapable of mitigating the difference between the training and target domains. In practice, unfortunately, training a DR model for each target domain to avoid domain shift is often a difficult task as it requires additional time, storage, and domain-specific data labeling, which are not always available. To address this problem, in this paper, we propose a novel DR framework named Disentangled Dense Retrieval (DDR) to support effective and flexible domain adaptation for DR models. DDR consists of a Relevance Estimation Module (REM) for modeling domain-invariant matching patterns and several Domain Adaption Modules (DAMs) for modeling domain-specific features of multiple target corpora. By making the REM and DAMs disentangled, DDR enables a flexible training paradigm in which REM is trained with supervision once and DAMs are trained with unsupervised data. Comprehensive experiments in different domains and languages show that DDR significantly improves ranking performance compared to strong DR baselines and substantially outperforms traditional retrieval methods in most scenarios.

preprint2022arXiv

Hard Negatives or False Negatives: Correcting Pooling Bias in Training Neural Ranking Models

Neural ranking models (NRMs) have become one of the most important techniques in information retrieval (IR). Due to the limitation of relevance labels, the training of NRMs heavily relies on negative sampling over unlabeled data. In general machine learning scenarios, it has shown that training with hard negatives (i.e., samples that are close to positives) could lead to better performance. Surprisingly, we find opposite results from our empirical studies in IR. When sampling top-ranked results (excluding the labeled positives) as negatives from a stronger retriever, the performance of the learned NRM becomes even worse. Based on our investigation, the superficial reason is that there are more false negatives (i.e., unlabeled positives) in the top-ranked results with a stronger retriever, which may hurt the training process; The root is the existence of pooling bias in the dataset constructing process, where annotators only judge and label very few samples selected by some basic retrievers. Therefore, in principle, we can formulate the false negative issue in training NRMs as learning from labeled datasets with pooling bias. To solve this problem, we propose a novel Coupled Estimation Technique (CET) that learns both a relevance model and a selection model simultaneously to correct the pooling bias for training NRMs. Empirical results on three retrieval benchmarks show that NRMs trained with our technique can achieve significant gains on ranking effectiveness against other baseline strategies.

preprint2022arXiv

Simulating and Modeling the Risk of Conversational Search

In conversational search, agents can interact with users by asking clarifying questions to increase their chance to find better results. Many recent works and shared tasks in both NLP and IR communities have focused on identifying the need of asking clarifying questions and methodologies of generating them. These works assume asking clarifying questions is a safe alternative to retrieving results. As existing conversational search models are far from perfect, it's possible and common that they could retrieve or generate bad clarifying questions. Asking too many clarifying questions can also drain user's patience when the user prefers searching efficiency over correctness. Hence, these models can get backfired and harm user's search experience because of these risks by asking clarifying questions. In this work, we propose a simulation framework to simulate the risk of asking questions in conversational search and further revise a risk-aware conversational search model to control the risk. We show the model's robustness and effectiveness through extensive experiments on three conversations datasets, including MSDialog, Ubuntu Dialog Corpus, and Opendialkg in which we compare it with multiple baselines. We show that the risk-control module can work with two different re-ranker models and outperform all the baselines in most of our experiments.

preprint2021arXiv

Controlling the Risk of Conversational Search via Reinforcement Learning

Users often formulate their search queries with immature language without well-developed keywords and complete structures. Such queries fail to express their true information needs and raise ambiguity as fragmental language often yield various interpretations and aspects. This gives search engines a hard time processing and understanding the query, and eventually leads to unsatisfactory retrieval results. An alternative approach to direct answer while facing an ambiguous query is to proactively ask clarifying questions to the user. Recent years have seen many works and shared tasks from both NLP and IR community about identifying the need for asking clarifying question and methodology to generate them. An often neglected fact by these works is that although sometimes the need for clarifying questions is correctly recognized, the clarifying questions these system generate are still off-topic and dissatisfaction provoking to users and may just cause users to leave the conversation. In this work, we propose a risk-aware conversational search agent model to balance the risk of answering user's query and asking clarifying questions. The agent is fully aware that asking clarifying questions can potentially collect more information from user, but it will compare all the choices it has and evaluate the risks. Only after then, it will make decision between answering or asking. To demonstrate that our system is able to retrieve better answers, we conduct experiments on the MSDialog dataset which contains real-world customer service conversations from Microsoft products community. We also purpose a reinforcement learning strategy which allows us to train our model on the original dataset directly and saves us from any further data annotation efforts. Our experiment results show that our risk-aware conversational search agent is able to significantly outperform strong non-risk-aware baselines.

preprint2021arXiv

Maximizing Marginal Fairness for Dynamic Learning to Rank

Rankings, especially those in search and recommendation systems, often determine how people access information and how information is exposed to people. Therefore, how to balance the relevance and fairness of information exposure is considered as one of the key problems for modern IR systems. As conventional ranking frameworks that myopically sorts documents with their relevance will inevitably introduce unfair result exposure, recent studies on ranking fairness mostly focus on dynamic ranking paradigms where result rankings can be adapted in real-time to support fairness in groups (i.e., races, genders, etc.). Existing studies on fairness in dynamic learning to rank, however, often achieve the overall fairness of document exposure in ranked lists by significantly sacrificing the performance of result relevance and fairness on the top results. To address this problem, we propose a fair and unbiased ranking method named Maximal Marginal Fairness (MMF). The algorithm integrates unbiased estimators for both relevance and merit-based fairness while providing an explicit controller that balances the selection of documents to maximize the marginal relevance and fairness in top-k results. Theoretical and empirical analysis shows that, with small compromises on long list fairness, our method achieves superior efficiency and effectiveness comparing to the state-of-the-art algorithms in both relevance and fairness for top-k rankings.

preprint2020arXiv

A Transformer-based Embedding Model for Personalized Product Search

Product search is an important way for people to browse and purchase items on E-commerce platforms. While customers tend to make choices based on their personal tastes and preferences, analysis of commercial product search logs has shown that personalization does not always improve product search quality. Most existing product search techniques, however, conduct undifferentiated personalization across search sessions. They either use a fixed coefficient to control the influence of personalization or let personalization take effect all the time with an attention mechanism. The only notable exception is the recently proposed zero-attention model (ZAM) that can adaptively adjust the effect of personalization by allowing the query to attend to a zero vector. Nonetheless, in ZAM, personalization can act at most as equally important as the query and the representations of items are static across the collection regardless of the items co-occurring in the user's historical purchases. Aware of these limitations, we propose a transformer-based embedding model (TEM) for personalized product search, which could dynamically control the influence of personalization by encoding the sequence of query and user's purchase history with a transformer architecture. Personalization could have a dominant impact when necessary and interactions between items can be taken into consideration when computing attention weights. Experimental results show that TEM outperforms state-of-the-art personalization product retrieval models significantly.

preprint2020arXiv

Analysis of Multivariate Scoring Functions for Automatic Unbiased Learning to Rank

Leveraging biased click data for optimizing learning to rank systems has been a popular approach in information retrieval. Because click data is often noisy and biased, a variety of methods have been proposed to construct unbiased learning to rank (ULTR) algorithms for the learning of unbiased ranking models. Among them, automatic unbiased learning to rank (AutoULTR) algorithms that jointly learn user bias models (i.e., propensity models) with unbiased rankers have received a lot of attention due to their superior performance and low deployment cost in practice. Despite their differences in theories and algorithm design, existing studies on ULTR usually use uni-variate ranking functions to score each document or result independently. On the other hand, recent advances in context-aware learning-to-rank models have shown that multivariate scoring functions, which read multiple documents together and predict their ranking scores jointly, are more powerful than uni-variate ranking functions in ranking tasks with human-annotated relevance labels. Whether such superior performance would hold in ULTR with noisy data, however, is mostly unknown. In this paper, we investigate existing multivariate scoring functions and AutoULTR algorithms in theory and prove that permutation invariance is a crucial factor that determines whether a context-aware learning-to-rank model could be applied to existing AutoULTR framework. Our experiments with synthetic clicks on two large-scale benchmark datasets show that AutoULTR models with permutation-invariant multivariate scoring functions significantly outperform those with uni-variate scoring functions and permutation-variant multivariate scoring functions.

preprint2020arXiv

E-commerce Recommendation with Weighted Expected Utility

Different from shopping at retail stores, consumers on e-commerce platforms usually cannot touch or try products before purchasing, which means that they have to make decisions when they are uncertain about the outcome (e.g., satisfaction level) of purchasing a product. To study people's preferences, economics researchers have proposed the hypothesis of Expected Utility (EU) that models the subject value associated with an individual's choice as the statistical expectations of that individual's valuations of the outcomes of this choice. Despite its success in studies of game theory and decision theory, the effectiveness of EU, however, is mostly unknown in e-commerce recommendation systems. Previous research on e-commerce recommendation interprets the utility of purchase decisions either as a function of the consumed quantity of the product or as the gain of sellers/buyers in the monetary sense. As most consumers just purchase one unit of a product at a time and most alternatives have similar prices, such modeling of purchase utility is likely to be inaccurate in practice. In this paper, we interpret purchase utility as the satisfaction level a consumer gets from a product and propose a recommendation framework using EU to model consumers' behavioral patterns. We assume that consumer estimates the expected utilities of all the alternatives and choose products with maximum expected utility for each purchase. To deal with the potential psychological biases of each consumer, we introduce the usage of Probability Weight Function (PWF) and design our algorithm based on Weighted Expected Utility (WEU). Empirical study on real-world e-commerce datasets shows that our proposed ranking-based recommendation framework achieves statistically significant improvement against both classical Collaborative Filtering/Latent Factor Models and state-of-the-art deep models in top-K recommendation.

preprint2020arXiv

Review Regularized Neural Collaborative Filtering

In recent years, text-aware collaborative filtering methods have been proposed to address essential challenges in recommendations such as data sparsity, cold start problem, and long-tail distribution. However, many of these text-oriented methods rely heavily on the availability of text information for every user and item, which obviously does not hold in real-world scenarios. Furthermore, specially designed network structures for text processing are highly inefficient for on-line serving and are hard to integrate into current systems. In this paper, we propose a flexible neural recommendation framework, named Review Regularized Recommendation, short as R3. It consists of a neural collaborative filtering part that focuses on prediction output, and a text processing part that serves as a regularizer. This modular design incorporates text information as richer data sources in the training phase while being highly friendly for on-line serving as it needs no on-the-fly text processing in serving time. Our preliminary results show that by using a simple text processing approach, it could achieve better prediction performance than state-of-the-art text-aware methods.

preprint2020arXiv

SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval

In learning-to-rank for information retrieval, a ranking model is automatically learned from the data and then utilized to rank the sets of retrieved documents. Therefore, an ideal ranking model would be a mapping from a document set to a permutation on the set, and should satisfy two critical requirements: (1)~it should have the ability to model cross-document interactions so as to capture local context information in a query; (2)~it should be permutation-invariant, which means that any permutation of the inputted documents would not change the output ranking. Previous studies on learning-to-rank either design uni-variate scoring functions that score each document separately, and thus failed to model the cross-document interactions; or construct multivariate scoring functions that score documents sequentially, which inevitably sacrifice the permutation invariance requirement. In this paper, we propose a neural learning-to-rank model called SetRank which directly learns a permutation-invariant ranking model defined on document sets of any size. SetRank employs a stack of (induced) multi-head self attention blocks as its key component for learning the embeddings for all of the retrieved documents jointly. The self-attention mechanism not only helps SetRank to capture the local context information from cross-document interactions, but also to learn permutation-equivariant representations for the inputted documents, which therefore achieving a permutation-invariant ranking model. Experimental results on three large scale benchmarks showed that the SetRank significantly outperformed the baselines include the traditional learning-to-rank models and state-of-the-art Neural IR models.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint