Yuexing Hao

Huabin Diao, Gongyan Li, Shaoyun Xu et al.

At present, the quantification methods of neural network models are mainly divided into post-training quantization (PTQ) and quantization aware training (QAT). Post-training quantization only need a small part of the data to complete the quantification process, but the performance of its quantitative model is not as good as the quantization aware training. This paper presents a novel quantification method called Attention Round. This method gives parameters w the opportunity to be mapped to all possible quantized values, rather than just the two quantized values nearby w in the process of quantization. The probability of being mapped to different quantified values is negatively correlated with the distance between the quantified values and w, and decay with a Gaussian function. In addition, this paper uses the lossy coding length as a measure to assign bit widths to the different layers of the model to solve the problem of mixed precision quantization, which effectively avoids to solve combinatorial optimization problem. This paper also performs quantitative experiments on different models, the results confirm the effectiveness of the proposed method. For ResNet18 and MobileNetV2, the post-training quantization proposed in this paper only require 1,024 training data and 10 minutes to complete the quantization process, which can achieve quantization performance on par with quantization aware training.

Yue Huang, Chujie Gao, Siyuan Wu et al.

Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns regarding trustworthiness across dimensions. This paper presents a comprehensive framework to address these challenges through three key contributions. First, we systematically review global AI governance laws and policies from governments and regulatory bodies, as well as industry practices and standards. Based on this analysis, we propose a set of guiding principles for GenFMs, developed through extensive multidisciplinary collaboration that integrates technical, ethical, legal, and societal perspectives. Second, we introduce TrustGen, the first dynamic benchmarking platform designed to evaluate trustworthiness across multiple dimensions and model types, including text-to-image, large language, and vision-language models. TrustGen leverages modular components--metadata curation, test case generation, and contextual variation--to enable adaptive and iterative assessments, overcoming the limitations of static evaluation methods. Using TrustGen, we reveal significant progress in trustworthiness while identifying persistent challenges. Finally, we provide an in-depth discussion of the challenges and future directions for trustworthy GenFMs, which reveals the complex, evolving nature of trustworthiness, highlighting the nuanced trade-offs between utility and trustworthiness, and consideration for various downstream applications, identifying persistent challenges and providing a strategic roadmap for future research. This work establishes a holistic framework for advancing trustworthiness in GenAI, paving the way for safer and more responsible integration of GenFMs into critical applications. To facilitate advancement in the community, we release the toolkit for dynamic evaluation.

Yuexing Hao, Jason M. Holmes, Jared Hobson et al.

In-basket message interactions play a crucial role in physician-patient communication, occurring during all phases (pre-, during, and post) of a patient's care journey. However, responding to these patients' inquiries has become a significant burden on healthcare workflows, consuming considerable time for clinical care teams. To address this, we introduce RadOnc-GPT, a specialized Large Language Model (LLM) powered by GPT-4 that has been designed with a focus on radiotherapeutic treatment of prostate cancer with advanced prompt engineering, and specifically designed to assist in generating responses. We integrated RadOnc-GPT with patient electronic health records (EHR) from both the hospital-wide EHR database and an internal, radiation-oncology-specific database. RadOnc-GPT was evaluated on 158 previously recorded in-basket message interactions. Quantitative natural language processing (NLP) analysis and two grading studies with clinicians and nurses were used to assess RadOnc-GPT's responses. Our findings indicate that RadOnc-GPT slightly outperformed the clinical care team in "Clarity" and "Empathy," while achieving comparable scores in "Completeness" and "Correctness." RadOnc-GPT is estimated to save 5.2 minutes per message for nurses and 2.4 minutes for clinicians, from reading the inquiry to sending the response. Employing RadOnc-GPT for in-basket message draft generation has the potential to alleviate the workload of clinical care teams and reduce healthcare costs by producing high-quality, timely responses.

Xiaomin Li, Jianheng Hou, Zheyuan Deng et al.

Large reasoning models (LRMs) increasingly expose chain-of-thought-like reasoning for transparency, verification, and deliberate problem solving. This creates a safety blind spot: harmful or policy-violating content may appear in reasoning traces even when final answers appear safe. We test whether final-answer safety is a sufficient proxy for the full reasoning-answer trajectory by scoring both stages under a unified twenty-principle safety rubric. Using prompts from seven public harmfulness and jailbreak sources, plus four out-of-distribution (OOD) sources, we evaluate 15 open-weight and API-based LRMs across 41K prompts per model. Reasoning traces consistently reveal additional safety risks beyond final answers, especially in high-severity stage-wise failures: leak cases, where unsafe reasoning precedes a safe-looking answer, and escape cases, where benign-looking reasoning precedes an unsafe final response. Principle-level analysis shows that risk concentrates in misinformation, legal compliance, discrimination, physical harm, and psychological harm. We further propose adaptive multi-principle steering, a white-box test-time mitigation that learns one unsafe-to-safe activation direction per safety principle and activates only directions whose current hidden state is closer to the unsafe than safe centroid. On three steerable open reasoning models, adaptive steering reduces unsafe counts in both reasoning traces and final answers on held-out and OOD benchmarks. DeepSeek-R1-Qwen-7B achieves a 40.8% average unsafe-count reduction while retaining 97.7% macro-averaged accuracy on BBH, GSM8K, and MMLU. These results suggest that LRM safety should be evaluated and mitigated over the full exposed reasoning-answer trajectory, not only at the final-answer stage.

Yue Huang, Zhengzhe Jiang, Yuchen Ma et al.

Understanding how and why large language models (LLMs) fail is becoming a central challenge as models rapidly evolve and static evaluations fall behind. While automated probing has been enabled by dynamic test generation, existing approaches often discover isolated failure cases, lack principled control over exploration, and provide limited insight into the underlying structure of model weaknesses. We propose ProbeLLM, a benchmark-agnostic automated probing framework that elevates weakness discovery from individual failures to structured failure modes. ProbeLLM formulates probing as a hierarchical Monte Carlo Tree Search, explicitly allocating limited probing budgets between global exploration of new failure regions and local refinement of recurring error patterns. By restricting probing to verifiable test cases and leveraging tool-augmented generation and verification, ProbeLLM grounds failure discovery in reliable evidence. Discovered failures are further consolidated into interpretable failure modes via failure-aware embeddings and boundary-aware induction. Across diverse benchmarks and LLMs, ProbeLLM reveals substantially broader, cleaner, and more fine-grained failure landscapes than static benchmarks and prior automated methods, supporting a shift from case-centric evaluation toward principled weakness discovery.

Yue Huang, Yuchen Ma, Jiayi Ye et al.

Interactive narrative tasks require LLMs to sustain a coherent, evolving story while adapting to a user over multiple turns. However, suitable benchmarks for this setting are limited: existing evaluations often focus on static prompts, isolated story generations, or post-hoc ratings, and therefore miss whether models can jointly manage story generation, long-context state and pacing, character simulation, empathic personalization, and story-grounded artifacts. We introduce NARRA-Gym, an executable evaluation environment that turns a sparse emotional seed into a complete interactive story episode and logs the full model-in-the-loop trajectory, including story construction, memory updates, planning, pacing interventions, and optional artifact synthesis. We evaluate nine frontier LLMs using a controlled LLM-as-judge sweep over eight benchmark personas and a human evaluation in which participants rate customized model outputs. Our results show substantial variation across models, personas, and evaluation dimensions: models that produce fluent stories can still fail on robustness, user experience, or resistance-sensitive personalization. These findings suggest that interactive narrative offers a useful benchmark for evaluating long-horizon, user-adaptive LLM behavior beyond isolated story quality.

Yuexing Hao, Kumail Alhamoud, Hyewon Jeong et al.

Large Language Models (LLMs) have demonstrated remarkable performance on various medical question-answering (QA) benchmarks, including standardized medical exams. However, correct answers alone do not ensure correct logic, and models may reach accurate conclusions through flawed processes. In this study, we introduce the MedPAIR (Medical Dataset Comparing Physicians and AI Relevance Estimation and Question Answering) dataset to evaluate how physician trainees and LLMs prioritize relevant information when answering QA questions. We obtain annotations on 1,300 QA pairs from 36 physician trainees, labeling each sentence within the question components for relevance. We compare these relevance estimates to those for LLMs, and further evaluate the impact of these "relevant" subsets on downstream task performance for both physician trainees and LLMs. We find that LLMs are frequently not aligned with the content relevance estimates of physician trainees. After filtering out physician trainee-labeled irrelevant sentences, accuracy improves for both the trainees and the LLMs. All LLM and physician trainee-labeled data are available at: http://medpair.csail.mit.edu/.

Yuexing Hao, Tiancheng Yuan, Yuting Yang et al.

Dairy owners spend significant effort to keep their animals healthy. There is good reason to hope that technologies such as computer vision and artificial intelligence (AI) could reduce these costs, yet obstacles arise when adapting advanced tools to farming environments. In this work, we adapt AI tools to dairy cow teat localization, teat shape, and teat skin condition classifications. We also curate a data collection and analysis methodology for a Machine Learning (ML) pipeline. The resulting teat shape prediction model achieves a mean Average Precision (mAP) of 0.783, and the teat skin condition model achieves a mean average precision of 0.828. Our work leverages existing ML vision models to facilitate the individualized identification of teat health and skin conditions, applying AI to the dairy management industry.

Jason Holmes, Yuexing Hao, Mariana Borras-Osorio et al.

Manual labeling limits the scale, accuracy, and timeliness of patient outcomes research in radiation oncology. We present RadOnc-GPT, an autonomous large language model (LLM)-based agent capable of independently retrieving patient-specific information, iteratively assessing evidence, and returning structured outcomes. Our evaluation explicitly validates RadOnc-GPT across two clearly defined tiers of increasing complexity: (1) a structured quality assurance (QA) tier, assessing the accurate retrieval of demographic and radiotherapy treatment plan details, followed by (2) a complex clinical outcomes labeling tier involving determination of mandibular osteoradionecrosis (ORN) in head-and-neck cancer patients and detection of cancer recurrence in independent prostate and head-and-neck cancer cohorts requiring combined interpretation of structured and unstructured patient data. The QA tier establishes foundational trust in structured-data retrieval, a critical prerequisite for successful complex clinical outcome labeling.

Abinitha Gourabathina, Yuexing Hao, Walter Gerych et al.

Clinical robustness is critical to the safe deployment of medical Large Language Models (LLMs), but key questions remain about how LLMs and humans may differ in response to the real-world variability typified by clinical settings. To address this, we introduce MedPerturb, a dataset designed to systematically evaluate medical LLMs under controlled perturbations of clinical input. MedPerturb consists of clinical vignettes spanning a range of pathologies, each transformed along three axes: (1) gender modifications (e.g., gender-swapping or gender-removal); (2) style variation (e.g., uncertain phrasing or colloquial tone); and (3) format changes (e.g., LLM-generated multi-turn conversations or summaries). With MedPerturb, we release a dataset of 800 clinical contexts grounded in realistic input variability, outputs from four LLMs, and three human expert reads per clinical context. We use MedPerturb in two case studies to reveal how shifts in gender identity cues, language style, or format reflect diverging treatment selections between humans and LLMs. We find that LLMs are more sensitive to gender and style perturbations while human annotators are more sensitive to LLM-generated format perturbations such as clinical summaries. Our results highlight the need for evaluation frameworks that go beyond static benchmarks to assess the similarity between human clinician and LLM decisions under the variability characteristic of clinical settings.

Yuexing Hao, Yue Huang, Haoran Zhang et al.

Cutting-edge research in Artificial Intelligence (AI) requires considerable resources, including Graphics Processing Units (GPUs), data, and human resources. In this paper, we evaluate of the relationship between these resources and the scientific advancement of foundation models (FM). We reviewed 6517 FM papers published between 2022 to 2024, and surveyed 229 first-authors to the impact of computing resources on scientific output. We find that increased computing is correlated with national funding allocations and citations, but our findings don't observe the strong correlations with research environment (academic or industrial), domain, or study methodology. We advise that individuals and institutions focus on creating shared and affordable computing opportunities to lower the entry barrier for under-resourced researchers. These steps can help expand participation in FM research, foster diversity of ideas and contributors, and sustain innovation and progress in AI. The data will be available at: https://mit-calc.csail.mit.edu/

Rory Sayres, Yuexing Hao, Abbi Ward et al. · deepmind

Navigating health questions can be daunting in the modern information landscape. Large language models (LLMs) may provide tailored, accessible information, but also risk being inaccurate, biased or misleading. We present insights from 4 mixed-methods studies (total N=163), examining how people interact with LLMs for their own health questions. Qualitative studies revealed the importance of context-seeking in conversational AIs to elicit specific details a person may not volunteer or know to share. Context-seeking by LLMs was valued by participants, even if it meant deferring an answer for several turns. Incorporating these insights, we developed a "Wayfinding AI" to proactively solicit context. In a randomized, blinded study, participants rated the Wayfinding AI as more helpful, relevant, and tailored to their concerns compared to a baseline AI. These results demonstrate the strong impact of proactive context-seeking on conversational dynamics, and suggest design patterns for conversational AI to help navigate health topics.

Ruichu Cai, Fengzhu Wu, Zijian Li et al.

The recommendation system, relying on historical observational data to model the complex relationships among the users and items, has achieved great success in real-world applications. Selection bias is one of the most important issues of the existing observational data based approaches, which is actually caused by multiple types of unobserved exposure strategies (e.g. promotions and holiday effects). Though various methods have been proposed to address this problem, they are mainly relying on the implicit debiasing techniques but not explicitly modeling the unobserved exposure strategies. By explicitly Reconstructing Exposure STrategies (REST in short), we formalize the recommendation problem as the counterfactual reasoning and propose the debiased social recommendation method. In REST, we assume that the exposure of an item is controlled by the latent exposure strategies, the user, and the item. Based on the above generation process, we first provide the theoretical guarantee of our method via identification analysis. Second, we employ a variational auto-encoder to reconstruct the latent exposure strategies, with the help of the social networks and the items. Third, we devise a counterfactual reasoning based recommendation algorithm by leveraging the recovered exposure strategies. Experiments on four real-world datasets, including three published datasets and one private WeChat Official Account dataset, demonstrate significant improvements over several state-of-the-art methods.

Zijian Li, Ruichu Cai, Fengzhu Wu et al.

Sequential recommendation aims to choose the most suitable items for a user at a specific timestamp given historical behaviors. Existing methods usually model the user behavior sequence based on the transition-based methods like Markov Chain. However, these methods also implicitly assume that the users are independent of each other without considering the influence between users. In fact, this influence plays an important role in sequence recommendation since the behavior of a user is easily affected by others. Therefore, it is desirable to aggregate both user behaviors and the influence between users, which are evolved temporally and involved in the heterogeneous graph of users and items. In this paper, we incorporate dynamic user-item heterogeneous graphs to propose a novel sequential recommendation framework. As a result, the historical behaviors as well as the influence between users can be taken into consideration. To achieve this, we firstly formalize sequential recommendation as a problem to estimate conditional probability given temporal dynamic heterogeneous graphs and user behavior sequences. After that, we exploit the conditional random field to aggregate the heterogeneous graphs and user behaviors for probability estimation, and employ the pseudo-likelihood approach to derive a tractable objective function. Finally, we provide scalable and flexible implementations of the proposed framework. Experimental results on three real-world datasets not only demonstrate the effectiveness of our proposed method but also provide some insightful discoveries on sequential recommendation.

Ruichu Cai, Zhihao Liang, Boyan Xu et al.

Existing leading code comment generation approaches with the structure-to-sequence framework ignores the type information of the interpretation of the code, e.g., operator, string, etc. However, introducing the type information into the existing framework is non-trivial due to the hierarchical dependence among the type information. In order to address the issues above, we propose a Type Auxiliary Guiding encoder-decoder framework for the code comment generation task which considers the source code as an N-ary tree with type information associated with each node. Specifically, our framework is featured with a Type-associated Encoder and a Type-restricted Decoder which enables adaptive summarization of the source code. We further propose a hierarchical reinforcement learning method to resolve the training difficulties of our proposed framework. Extensive evaluations demonstrate the state-of-the-art performance of our framework with both the auto-evaluated metrics and case studies.

Suncong Zheng, Feng Wang, Hongyun Bao et al.

Joint extraction of entities and relations is an important task in information extraction. To tackle this problem, we firstly propose a novel tagging scheme that can convert the joint extraction task to a tagging problem. Then, based on our tagging scheme, we study different end-to-end models to extract entities and their relations directly, without identifying entities and relations separately. We conduct experiments on a public dataset produced by distant supervision method and the experimental results show that the tagging based methods are better than most of the existing pipelined and joint learning methods. What's more, the end-to-end model proposed in this paper, achieves the best results on the public dataset.