Zijun Yao

Amy Xin, Yunjia Qi, Zijun Yao et al. · pku

Specialized entity linking (EL) models are well-trained at mapping mentions to unique knowledge base (KB) entities according to a given context. However, specialized EL models struggle to disambiguate long-tail entities due to their limited training data. Meanwhile, extensively pre-trained large language models (LLMs) possess broader knowledge of uncommon entities. Yet, with a lack of specialized EL training, LLMs frequently fail to generate accurate KB entity names, limiting their standalone effectiveness in EL. With the observation that LLMs are more adept at context generation instead of EL execution, we introduce LLM-Augmented Entity Linking (LLMAEL), the first framework to enhance specialized EL models with LLM data augmentation. LLMAEL leverages off-the-shelf, tuning-free LLMs as context augmenters, generating entity descriptions to serve as additional input for specialized EL models. Experiments show that LLMAEL sets new state-of-the-art results across 6 widely adopted EL benchmarks: compared to prior methods that integrate tuning-free LLMs into EL, LLMAEL achieves an absolute 8.9% gain in EL accuracy. We release our code and datasets.

Zijun Yao, Yuanyong Chen, Xin Lv et al. · tsinghua

We present Visual Knowledge oriented Programming platform (VisKoP), a knowledge base question answering (KBQA) system that integrates human into the loop to edit and debug the knowledge base (KB) queries. VisKoP not only provides a neural program induction module, which converts natural language questions into knowledge oriented program language (KoPL), but also maps KoPL programs into graphical elements. KoPL programs can be edited with simple graphical operators, such as dragging to add knowledge operators and slot filling to designate operator arguments. Moreover, VisKoP provides auto-completion for its knowledge base schema and users can easily debug the KoPL program by checking its intermediate results. To facilitate the practical KBQA on a million-entity-level KB, we design a highly efficient KoPL execution engine for the back-end. Experiment results show that VisKoP is highly efficient and user interaction can fix a large portion of wrong KoPL programs to acquire the correct answer. The VisKoP online demo https://demoviskop.xlore.cn (Stable release of this paper) and https://viskop.xlore.cn (Beta release with new features), highly efficient KoPL engine https://pypi.org/project/kopl-engine, and screencast video https://youtu.be/zAbJtxFPTXo are now publicly available.

Zeyan Liu, Zijun Yao, Fengjun Li et al.

With ChatGPT under the spotlight, utilizing large language models (LLMs) to assist academic writing has drawn a significant amount of debate in the community. In this paper, we aim to present a comprehensive study of the detectability of ChatGPT-generated content within the academic literature, particularly focusing on the abstracts of scientific papers, to offer holistic support for the future development of LLM applications and policies in academia. Specifically, we first present GPABench2, a benchmarking dataset of over 2.8 million comparative samples of human-written, GPT-written, GPT-completed, and GPT-polished abstracts of scientific writing in computer science, physics, and humanities and social sciences. Second, we explore the methodology for detecting ChatGPT content. We start by examining the unsatisfactory performance of existing ChatGPT detecting tools and the challenges faced by human evaluators (including more than 240 researchers or students). We then test the hand-crafted linguistic features models as a baseline and develop a deep neural framework named CheckGPT to better capture the subtle and deep semantic and linguistic patterns in ChatGPT written literature. Last, we conduct comprehensive experiments to validate the proposed CheckGPT framework in each benchmarking task over different disciplines. To evaluate the detectability of ChatGPT content, we conduct extensive experiments on the transferability, prompt engineering, and robustness of CheckGPT.

Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Bin Liu et al.

Survival analysis plays a crucial role in many healthcare decisions, where the risk prediction for the events of interest can support an informative outlook for a patient's medical journey. Given the existence of data censoring, an effective way of survival analysis is to enforce the pairwise temporal concordance between censored and observed data, aiming to utilize the time interval before censoring as partially observed time-to-event labels for supervised learning. Although existing studies mostly employed ranking methods to pursue an ordering objective, contrastive methods which learn a discriminative embedding by having data contrast against each other, have not been explored thoroughly for survival analysis. Therefore, in this paper, we propose a novel Ontology-aware Temporality-based Contrastive Survival (OTCSurv) analysis framework that utilizes survival durations from both censored and observed data to define temporal distinctiveness and construct negative sample pairs with adjustable hardness for contrastive learning. Specifically, we first use an ontological encoder and a sequential self-attention encoder to represent the longitudinal EHR data with rich contexts. Second, we design a temporal contrastive loss to capture varying survival durations in a supervised setting through a hardness-aware negative sampling mechanism. Last, we incorporate the contrastive task into the time-to-event predictive task with multiple loss components. We conduct extensive experiments using a large EHR dataset to forecast the risk of hospitalized patients who are in danger of developing acute kidney injury (AKI), a critical and urgent medical condition. The effectiveness and explainability of the proposed model are validated through comprehensive quantitative and qualitative studies.

Yixiu Zhao, Xiaozhi Wang, Zijun Yao et al.

Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, we introduce a simple, lightweight, and broadly applicable method with a focus on isolating neurons that encode specific skills. Building upon prior work that identified "skill neurons" via soft prompt training on classification tasks, our approach extends the analysis to complex scenarios involving multiple skills. We correlate neuron activations with auxiliary metrics -- such as external labels and the model's own confidence score -- thereby uncovering interpretable and task-specific behaviors without the need for manual token aggregation. We empirically validate our method on tasks spanning open-ended text generation and natural language inference, demonstrating its ability to detect neurons that not only drive known skills but also reveal previously unidentified shortcuts in arithmetic reasoning on BigBench.

Hao Peng, Yunjia Qi, Xiaozhi Wang et al. · tsinghua

Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown strong potential in training LLMs. In this paper, we propose agentic reward modeling, a reward system that combines reward models with verifiable correctness signals from different aspects to provide reliable rewards. We empirically implement a reward agent, named RewardAgent, that combines human preference rewards with two verifiable signals: factuality and instruction following, to provide more reliable rewards. We conduct comprehensive experiments on existing reward model benchmarks and inference time best-of-n searches on real-world downstream tasks. RewardAgent significantly outperforms vanilla reward models, demonstrating its effectiveness. We further construct training preference pairs using RewardAgent and train an LLM with the DPO objective, achieving superior performance on various NLP benchmarks compared to conventional reward models. Our codes are publicly released to facilitate further research (https://github.com/THU-KEG/Agentic-Reward-Modeling).

Daniel Zhang-Li, Nianyi Lin, Jifan Yu et al.

Recent advancements in pretraining have demonstrated that modern Large Language Models (LLMs) possess the capability to effectively learn arithmetic operations. However, despite acknowledging the significance of digit order in arithmetic computation, current methodologies predominantly rely on sequential, step-by-step approaches for teaching LLMs arithmetic, resulting in a conclusion where obtaining better performance involves fine-grained step-by-step. Diverging from this conventional path, our work introduces a novel strategy that not only reevaluates the digit order by prioritizing output from the least significant digit but also incorporates a step-by-step methodology to substantially reduce complexity. We have developed and applied this method in a comprehensive set of experiments. Compared to the previous state-of-the-art (SOTA) method, our findings reveal an overall improvement of in accuracy while requiring only a third of the tokens typically used during training. For the purpose of facilitating replication and further research, we have made our code and dataset publicly available at \url{https://anonymous.4open.science/r/RAIT-9FB7/}.

Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Mei Liu et al.

Recent advancements in sequential modeling applied to Electronic Health Records (EHR) have greatly influenced prescription recommender systems. While the recent literature on drug recommendation has shown promising performance, the study of discovering a diversity of coexisting temporal relationships at the level of medical codes over consecutive visits remains less explored. The goal of this study can be motivated from two perspectives. First, there is a need to develop a sophisticated sequential model capable of disentangling the complex relationships across sequential visits. Second, it is crucial to establish multiple and diverse health profiles for the same patient to ensure a comprehensive consideration of different medical intents in drug recommendation. To achieve this goal, we introduce Attentive Recommendation with Contrasted Intents (ARCI), a multi-level transformer-based method designed to capture the different but coexisting temporal paths across a shared sequence of visits. Specifically, we propose a novel intent-aware method with contrastive learning, that links specialized medical intents of the patients to the transformer heads for extracting distinct temporal paths associated with different health profiles. We conducted experiments on two real-world datasets for the prescription recommendation task using both ranking and classification metrics. Our results demonstrate that ARCI has outperformed the state-of-the-art prescription recommendation methods and is capable of providing interpretable insights for healthcare practitioners.

Zhenglin Hua, Jinghan He, Zijun Yao et al.

Large vision-language models (LVLMs) have achieved remarkable performance on multimodal tasks. However, they still suffer from hallucinations, generating text inconsistent with visual input, posing significant risks in real-world applications. Existing approaches to address this issue focus on incorporating external knowledge bases, alignment training, or decoding strategies, all of which require substantial computational cost and time. Recent works try to explore more efficient alternatives by adjusting LVLMs' internal representations. Although promising, these methods may cause hallucinations to be insufficiently suppressed or lead to excessive interventions that negatively affect normal semantics. In this work, we leverage sparse autoencoders (SAEs) to identify semantic directions closely associated with faithfulness or hallucination, extracting more precise and disentangled hallucination-related representations. Our analysis demonstrates that interventions along the identified faithful direction can mitigate hallucinations, while those along the hallucinatory direction can exacerbate them. Building on these insights, we propose Steering LVLMs via SAE Latent Directions (SSL), a plug-and-play method based on SAE-derived latent directions to mitigate hallucinations in LVLMs. Extensive experiments demonstrate that SSL significantly outperforms existing decoding approaches in mitigating hallucinations, while maintaining transferability across different model architectures with negligible additional time overhead. The code is available at https://github.com/huazhenglin2003/SSL.

Shangqing Tu, Kejian Zhu, Yushi Bai et al.

The advancement of large language models (LLMs) relies on evaluation using public benchmarks, but data contamination can lead to overestimated performance. Previous researches focus on detecting contamination by determining whether the model has seen the exact same data during training. Besides, prior work has already shown that even training on data similar to benchmark data inflates performance, namely \emph{In-distribution contamination}. In this work, we argue that in-distribution contamination can lead to the performance drop on OOD benchmarks. To effectively detect in-distribution contamination, we propose DICE, a novel method that leverages the internal states of LLMs to locate-then-detect the contamination. DICE first identifies the most sensitive layer to contamination, then trains a classifier based on the internal states of that layer. Experiments reveal DICE's high accuracy in detecting in-distribution contamination across various LLMs and math reasoning datasets. We also show the generalization capability of the trained DICE detector, which is able to detect contamination across multiple benchmarks with similar distributions. Additionally, we find that DICE's predictions correlate with the performance of LLMs fine-tuned by either us or other organizations, achieving a coefficient of determination ($R^2$) between 0.61 and 0.75. The code and data are available at https://github.com/THU-KEG/DICE.

Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Cuncong Zhong et al.

Gene expression profiles obtained through DNA microarray have proven successful in providing critical information for cancer detection classifiers. However, the limited number of samples in these datasets poses a challenge to employ complex methodologies such as deep neural networks for sophisticated analysis. To address this "small data" dilemma, Meta-Learning has been introduced as a solution to enhance the optimization of machine learning models by utilizing similar datasets, thereby facilitating a quicker adaptation to target datasets without the requirement of sufficient samples. In this study, we present a meta-learning-based approach for predicting lung cancer from gene expression profiles. We apply this framework to well-established deep learning methodologies and employ four distinct datasets for the meta-learning tasks, where one as the target dataset and the rest as source datasets. Our approach is evaluated against both traditional and deep learning methodologies, and the results show the superior performance of meta-learning on augmented source data compared to the baselines trained on single datasets. Moreover, we conduct the comparative analysis between meta-learning and transfer learning methodologies to highlight the efficiency of the proposed approach in addressing the challenges associated with limited sample sizes. Finally, we incorporate the explainability study to illustrate the distinctiveness of decisions made by meta-learning.

Zijun Yao, Yantao Liu, Yanxu Chen et al.

Recently evolved large reasoning models (LRMs) show powerful performance in solving complex tasks with long chain-of-thought (CoT) reasoning capability. As these LRMs are mostly developed by post-training on formal reasoning tasks, whether they generalize the reasoning capability to help reduce hallucination in fact-seeking tasks remains unclear and debated. For instance, DeepSeek-R1 reports increased performance on SimpleQA, a fact-seeking benchmark, while OpenAI-o3 observes even severer hallucination. This discrepancy naturally raises the following research question: Are reasoning models more prone to hallucination? This paper addresses the question from three perspectives. (1) We first conduct a holistic evaluation for the hallucination in LRMs. Our analysis reveals that LRMs undergo a full post-training pipeline with cold start supervised fine-tuning (SFT) and verifiable reward RL generally alleviate their hallucination. In contrast, both distillation alone and RL training without cold start fine-tuning introduce more nuanced hallucinations. (2) To explore why different post-training pipelines alters the impact on hallucination in LRMs, we conduct behavior analysis. We characterize two critical cognitive behaviors that directly affect the factuality of a LRM: Flaw Repetition, where the surface-level reasoning attempts repeatedly follow the same underlying flawed logic, and Think-Answer Mismatch, where the final answer fails to faithfully match the previous CoT process. (3) Further, we investigate the mechanism behind the hallucination of LRMs from the perspective of model uncertainty. We find that increased hallucination of LRMs is usually associated with the misalignment between model uncertainty and factual accuracy. Our work provides an initial understanding of the hallucination in LRMs.

Yantao Liu, Zijun Yao, Rui Min et al.

Best-of-N (BoN) sampling, a common strategy for test-time scaling of Large Language Models (LLMs), relies on reward models to select the best candidate solution from multiple generations. However, traditional reward models often assign arbitrary and inconsistent scores, limiting their effectiveness. To address this, we propose a Pairwise Judge Reward Model (PariJudge RM) combined with a knockout tournament for BoN sampling. Instead of assigning absolute scores, given one math problem, PariJudge RM judges two candidate solutions' correctness with chain-of-thought reasoning simultaneously. This approach eliminates the need for scoring and enables cross-validation of solutions through parallel judgment. In the knockout tournament, PariJudge RM conducts pairwise Judgment between candidate solutions and eliminates the incorrect ones iteratively. We construct PairJudge-432K, a large-scale dataset of 432K pairwise judgments derived from NumiaMath and annotated using \texttt{gemini-1.5-flash}, and train the PariJudge RM via supervised fine-tuning. Experiments on MATH-500 and the Olympiad Bench demonstrate significant improvements over baseline reward models. And a 40\% to 60\% relative improvement is achieved on the top 50\% challenging problems.

Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Dongjie Wang et al.

Medical ontology graphs map external knowledge to medical codes in electronic health records via structured relationships. By leveraging domain-approved connections (e.g., parent-child), predictive models can generate richer medical concept representations by incorporating contextual information from related concepts. However, existing literature primarily focuses on incorporating domain knowledge from a single ontology system, or from multiple ontology systems (e.g., diseases, drugs, and procedures) in isolation, without integrating them into a unified learning structure. Consequently, concept representation learning often remains limited to intra-ontology relationships, overlooking cross-ontology connections. In this paper, we propose LINKO, a large language model (LLM)-augmented integrative ontology learning framework that leverages multiple ontology graphs simultaneously by enabling dual-axis knowledge propagation both within and across heterogeneous ontology systems to enhance medical concept representation learning. Specifically, LINKO first employs LLMs to provide a graph-retrieval-augmented initialization for ontology concept embedding, through an engineered prompt that includes concept descriptions, and is further augmented with ontology context. Second, our method jointly learns the medical concepts in diverse ontology graphs by performing knowledge propagation in two axes: (1) intra-ontology vertical propagation across hierarchical ontology levels and (2) inter-ontology horizontal propagation within every level in parallel. Last, through extensive experiments on two public datasets, we validate the superior performance of LINKO over state-of-the-art baselines. As a plug-in encoder compatible with existing EHR predictive models, LINKO further demonstrates enhanced robustness in scenarios involving limited data availability and rare disease prediction.

Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Bin Liu et al.

Survival analysis (SA) models have been widely studied in mining electronic health records (EHRs), particularly in forecasting the risk of critical conditions for prioritizing high-risk patients. However, their vulnerability to adversarial attacks is much less explored in the literature. Developing black-box perturbation algorithms and evaluating their impact on state-of-the-art survival models brings two benefits to medical applications. First, it can effectively evaluate the robustness of models in pre-deployment testing. Also, exploring how subtle perturbations would result in significantly different outcomes can provide counterfactual insights into the clinical interpretation of model prediction. In this work, we introduce SurvAttack, a novel black-box adversarial attack framework leveraging subtle clinically compatible, and semantically consistent perturbations on longitudinal EHRs to degrade survival models' predictive performance. We specifically develop a greedy algorithm to manipulate medical codes with various adversarial actions throughout a patient's medical history. Then, these adversarial actions are prioritized using a composite scoring strategy based on multi-aspect perturbation quality, including saliency, perturbation stealthiness, and clinical meaningfulness. The proposed adversarial EHR perturbation algorithm is then used in an efficient SA-specific strategy to attack a survival model when estimating the temporal ranking of survival urgency for patients. To demonstrate the significance of our work, we conduct extensive experiments, including baseline comparisons, explainability analysis, and case studies. The experimental results affirm our research's effectiveness in illustrating the vulnerabilities of patient survival models, model interpretation, and ultimately contributing to healthcare quality.

Yantao Liu, Zhao Zhang, Zijun Yao et al.

Large Language Models (LLMs) have shown significant promise as copilots in various tasks. Local deployment of LLMs on edge devices is necessary when handling privacy-sensitive data or latency-sensitive tasks. The computational constraints of such devices make direct deployment of powerful large-scale LLMs impractical, necessitating the Knowledge Distillation from large-scale models to lightweight models. Lots of work has been done to elicit diversity and quality training examples from LLMs, but little attention has been paid to aligning teacher instructional content based on student preferences, akin to "responsive teaching" in pedagogy. Thus, we propose ARTE, dubbed Aligning TeacheR with StudenT PreferencEs, a framework that aligns the teacher model with student preferences to generate tailored training examples for Knowledge Distillation. Specifically, we elicit draft questions and rationales from the teacher model, then collect student preferences on these questions and rationales using students' performance with in-context learning as a proxy, and finally align the teacher model with student preferences. In the end, we repeat the first step with the aligned teacher model to elicit tailored training examples for the student model on the target task. Extensive experiments on academic benchmarks demonstrate the superiority of ARTE over existing instruction-tuning datasets distilled from powerful LLMs. Moreover, we thoroughly investigate the generalization of ARTE, including the generalization of fine-tuned student models in reasoning ability and the generalization of aligned teacher models to generate tailored training data across tasks and students. In summary, our contributions lie in proposing a novel framework for tailored training example generation, demonstrating its efficacy in experiments, and investigating the generalization of both student & aligned teacher models in ARTE.

Mohamed Ghalwash, Zijun Yao, Prithwish Chakraborty et al.

Despite the large number of patients in Electronic Health Records (EHRs), the subset of usable data for modeling outcomes of specific phenotypes are often imbalanced and of modest size. This can be attributed to the uneven coverage of medical concepts in EHRs. In this paper, we propose OMTL, an Ontology-driven Multi-Task Learning framework, that is designed to overcome such data limitations. The key contribution of our work is the effective use of knowledge from a predefined well-established medical relationship graph (ontology) to construct a novel deep learning network architecture that mirrors this ontology. It can effectively leverage knowledge from a well-established medical relationship graph (ontology) by constructing a deep learning network architecture that mirrors this graph. This enables common representations to be shared across related phenotypes, and was found to improve the learning performance. The proposed OMTL naturally allows for multitask learning of different phenotypes on distinct predictive tasks. These phenotypes are tied together by their semantic distance according to the external medical ontology. Using the publicly available MIMIC-III database, we evaluate OMTL and demonstrate its efficacy on several real patient outcome predictions over state-of-the-art multi-task learning schemes.

Mohamed Ghalwash, Zijun Yao, Prithwish Chakrabotry et al.

Increased availability of electronic health records (EHR) has enabled researchers to study various medical questions. Cohort selection for the hypothesis under investigation is one of the main consideration for EHR analysis. For uncommon diseases, cohorts extracted from EHRs contain very limited number of records - hampering the robustness of any analysis. Data augmentation methods have been successfully applied in other domains to address this issue mainly using simulated records. In this paper, we present ODVICE, a data augmentation framework that leverages the medical concept ontology to systematically augment records using a novel ontologically guided Monte-Carlo graph spanning algorithm. The tool allows end users to specify a small set of interactive controls to control the augmentation process. We analyze the importance of ODVICE by conducting studies on MIMIC-III dataset for two learning tasks. Our results demonstrate the predictive performance of ODVICE augmented cohorts, showing ~30% improvement in area under the curve (AUC) over the non-augmented dataset and other data augmentation strategies.