Xinyan Zhao

Amazon AGI, Aaron Langford, Aayush Shah et al. · amazon-science

We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highly-capable multimodal model with the best combination of accuracy, speed, and cost for a wide range of tasks. Amazon Nova Lite is a low-cost multimodal model that is lightning fast for processing images, video, documents and text. Amazon Nova Micro is a text-only model that delivers our lowest-latency responses at very low cost. Amazon Nova Canvas is an image generation model that creates professional grade images with rich customization controls. Amazon Nova Reel is a video generation model offering high-quality outputs, customization, and motion control. Our models were built responsibly and with a commitment to customer trust, security, and reliability. We report benchmarking results for core capabilities, agentic performance, long context, functional adaptation, runtime performance, and human evaluation.

Zhuoer Wang, Leonardo F. R. Ribeiro, Alexandros Papangelis et al. · amazon-science, microsoft-research

API call generation is the cornerstone of large language models' tool-using ability that provides access to the larger world. However, existing supervised and in-context learning approaches suffer from high training costs, poor data efficiency, and generated API calls that can be unfaithful to the API documentation and the user's request. To address these limitations, we propose an output-side optimization approach called FANTASE. Two of the unique contributions of FANTASE are its State-Tracked Constrained Decoding (SCD) and Reranking components. SCD dynamically incorporates appropriate API constraints in the form of Token Search Trie for efficient and guaranteed generation faithfulness with respect to the API documentation. The Reranking component efficiently brings in the supervised signal by leveraging a lightweight model as the discriminator to rerank the beam-searched candidate generations of the large language model. We demonstrate the superior performance of FANTASE in API call generation accuracy, inference efficiency, and context efficiency with DSTC8 and API Bank datasets.

Yohan Jo, Xinyan Zhao, Arijit Biswas et al.

While most task-oriented dialogues assume conversations between the agent and one user at a time, dialogue systems are increasingly expected to communicate with multiple users simultaneously who make decisions collaboratively. To facilitate development of such systems, we release the Multi-User MultiWOZ dataset: task-oriented dialogues among two users and one agent. To collect this dataset, each user utterance from MultiWOZ 2.2 was replaced with a small chat between two users that is semantically and pragmatically consistent with the original user utterance, thus resulting in the same dialogue state and system response. These dialogues reflect interesting dynamics of collaborative decision-making in task-oriented scenarios, e.g., social chatter and deliberation. Supported by this data, we propose the novel task of multi-user contextual query rewriting: to rewrite a task-oriented chat between two users as a concise task-oriented query that retains only task-relevant information and that is directly consumable by the dialogue system. We demonstrate that in multi-user dialogues, using predicted rewrites substantially improves dialogue state tracking without modifying existing dialogue systems that are trained for single-user dialogues. Further, this method surpasses training a medium-sized model directly on multi-user dialogues and generalizes to unseen domains.

Jiazhao Li, Corey Lester, Xinyan Zhao et al.

The language used by physicians and health professionals in prescription directions includes medical jargon and implicit directives and causes much confusion among patients. Human intervention to simplify the language at the pharmacies may introduce additional errors that can lead to potentially severe health outcomes. We propose a novel machine translation-based approach, PharmMT, to automatically and reliably simplify prescription directions into patient-friendly language, thereby significantly reducing pharmacist workload. We evaluate the proposed approach over a dataset consisting of over 530K prescriptions obtained from a large mail-order pharmacy. The end-to-end system achieves a BLEU score of 60.27 against the reference directions generated by pharmacists, a 39.6% relative improvement over the rule-based normalization. Pharmacists judged 94.3% of the simplified directions as usable as-is or with minimal changes. This work demonstrates the feasibility of a machine translation-based tool for simplifying prescription directions in real-life.

Ruijia Zhang, Xinyan Zhao, Ruixiang Wang et al.

LLM-based multi-agent systems exhibit strong collaborative capabilities but often suffer from redundant communication and excessive token overhead. Existing methods typically enhance efficiency through pretrained GNNs or greedy algorithms, but often isolate pre- and post-task optimization, lacking a unified strategy. To this end, we present SafeSieve, a progressive and adaptive multi-agent pruning algorithm that dynamically refines the inter-agent communication through a novel dual-mechanism. SafeSieve integrates initial LLM-based semantic evaluation with accumulated performance feedback, enabling a smooth transition from heuristic initialization to experience-driven refinement. Unlike existing greedy Top-k pruning methods, SafeSieve employs 0-extension clustering to preserve structurally coherent agent groups while eliminating ineffective links. Experiments across benchmarks (SVAMP, HumanEval, etc.) showcase that SafeSieve achieves 94.01% average accuracy while reducing token usage by 12.4%-27.8%. Results further demonstrate robustness under prompt injection attacks (1.23% average accuracy drop). In heterogeneous settings, SafeSieve reduces deployment costs by 13.3% while maintaining performance. These results establish SafeSieve as a robust, efficient, and scalable framework for practical multi-agent systems. Our code can be found in https://anonymous.4open.science/r/SafeSieve-D8F2FFUN.

Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna et al. · amazon-science

Safety reasoning is a recent paradigm where LLMs reason over safety policies before generating responses, thereby mitigating limitations in existing safety measures such as over-refusal and jailbreak vulnerabilities. However, implementing this paradigm is challenging due to the resource-intensive process of creating high-quality policy-embedded chain-of-thought (CoT) datasets while ensuring reasoning remains accurate and free from hallucinations or policy conflicts. To tackle this, we propose AIDSAFE: Agentic Iterative Deliberation for Safety Reasoning, a novel data generation recipe that leverages multi-agent deliberation to iteratively expand reasoning on safety policies. A data refiner stage in AIDSAFE ensures high-quality outputs by eliminating repetitive, redundant, and deceptive thoughts. AIDSAFE-generated CoTs provide a strong foundation for supervised fine-tuning (SFT)-based safety training. Additionally, to address the need of preference data in alignment stages, such as DPO training, we introduce a supplemental recipe that uses belief augmentation to create distinct selected and rejected CoT samples. Our evaluations demonstrate that AIDSAFE-generated CoTs achieve superior policy adherence and reasoning quality. Consequently, we show that fine-tuning open-source LLMs on these CoTs can significantly improve safety generalization and jailbreak robustness while maintaining acceptable utility and over-refusal accuracy. AIDSAFE-generated CoT datasets can be found here: https://huggingface.co/datasets/AmazonScience/AIDSAFE

Xinyan Zhao, V. G. Vinod Vydiswaran

Natural language explanations (NLEs) are a special form of data annotation in which annotators identify rationales (most significant text tokens) when assigning labels to data instances, and write out explanations for the labels in natural language based on the rationales. NLEs have been shown to capture human reasoning better, but not as beneficial for natural language inference (NLI). In this paper, we analyze two primary flaws in the way NLEs are currently used to train explanation generators for language inference tasks. We find that the explanation generators do not take into account the variability inherent in human explanation of labels, and that the current explanation generation models generate spurious explanations. To overcome these limitations, we propose a novel framework, LIREx, that incorporates both a rationale-enabled explanation generator and an instance selector to select only relevant, plausible NLEs to augment NLI models. When evaluated on the standardized SNLI data set, LIREx achieved an accuracy of 91.87%, an improvement of 0.32 over the baseline and matching the best-reported performance on the data set. It also achieves significantly better performance than previous studies when transferred to the out-of-domain MultiNLI data set. Qualitative analysis shows that LIREx generates flexible, faithful, and relevant NLEs that allow the model to be more robust to spurious explanations. The code is available at https://github.com/zhaoxy92/LIREx.

Gong Chen, Chaokun Zhang, Xinyan Zhao

Collaborative perception is vital for autonomous driving yet remains constrained by tight communication budgets. Earlier work reduced bandwidth by compressing full feature maps with fixed-rate encoders, which adapts poorly to a changing environment, and it further evolved into spatial selection methods that improve efficiency by focusing on salient regions, but this object-centric approach often sacrifices global context, weakening holistic scene understanding. To overcome these limitations, we introduce \textit{WhisperNet}, a bandwidth-aware framework that proposes a novel, receiver-centric paradigm for global coordination across agents. Senders generate lightweight saliency metadata, while the receiver formulates a global request plan that dynamically budgets feature contributions across agents and features, retrieving only the most informative features. A collaborative feature routing module then aligns related messages before fusion to ensure structural consistency. Extensive experiments show that WhisperNet achieves state-of-the-art performance, improving AP@0.7 on OPV2V by 2.4\% with only 0.5\% of the communication cost. As a plug-and-play component, it boosts strong baselines with merely 5\% of full bandwidth while maintaining robustness under localization noise. These results demonstrate that globally-coordinated allocation across \textit{what} and \textit{where} to share is the key to achieving efficient collaborative perception.

Chengshuai Zhao, Zhen Tan, Chau-Wai Wong et al.

Content analysis breaks down complex and unstructured texts into theory-informed numerical categories. Particularly, in social science, this process usually relies on multiple rounds of manual annotation, domain expert discussion, and rule-based refinement. In this paper, we introduce SCALE, a novel multi-agent framework that effectively $\underline{\textbf{S}}$imulates $\underline{\textbf{C}}$ontent $\underline{\textbf{A}}$nalysis via $\underline{\textbf{L}}$arge language model (LLM) ag$\underline{\textbf{E}}$nts. SCALE imitates key phases of content analysis, including text coding, collaborative discussion, and dynamic codebook evolution, capturing the reflective depth and adaptive discussions of human researchers. Furthermore, by integrating diverse modes of human intervention, SCALE is augmented with expert input to further enhance its performance. Extensive evaluations on real-world datasets demonstrate that SCALE achieves human-approximated performance across various complex content analysis tasks, offering an innovative potential for future social science research.

Xinyan Zhao, Yi-Ching Tang, Akshita Singh et al.

We introduce AbBiBench (Antibody Binding Benchmarking), a benchmarking framework for antibody binding affinity maturation and design. Unlike previous strategies that evaluate antibodies in isolation, typically by comparing them to natural sequences with metrics such as amino acid recovery rate or structural RMSD, AbBiBench instead treats the antibody-antigen (Ab-Ag) complex as the fundamental unit. It evaluates an antibody design's binding potential by measuring how well a protein model scores the full Ab-Ag complex. We first curate, standardize, and share more than 184,500 experimental measurements of antibody mutants across 14 antibodies and 9 antigens-including influenza, lysozyme, HER2, VEGF, integrin, Ang2, and SARS-CoV-2-covering both heavy-chain and light-chain mutations. Using these datasets, we systematically compare 15 protein models including masked language models, autoregressive language models, inverse folding models, diffusion-based generative models, and geometric graph models by comparing the correlation between model likelihood and experimental affinity values. Additionally, to demonstrate AbBiBench's generative utility, we apply it to antibody F045-092 in order to introduce binding to influenza H1N1. We sample new antibody variants with the top-performing models, rank them by the structural integrity and biophysical properties of the Ab-Ag complex, and assess them with in vitro ELISA binding assays. Our findings show that structure-conditioned inverse folding models outperform others in both affinity correlation and generation tasks. Overall, AbBiBench provides a unified, biologically grounded evaluation framework to facilitate the development of more effective, function-aware antibody design models.

Xinyan Zhao, Yuan Sun, Wenlin Liu et al.

This study is among the first to develop different prototypes of generative artificial intelligence (GenAI) chatbots powered by GPT-4 to communicate hurricane preparedness information to diverse residents. Drawing from the Computers Are Social Actors paradigm and the literature on disaster vulnerability and cultural tailoring, we conducted a between-subjects experiment with 441 Black, Hispanic, and Caucasian residents of Florida. Our results suggest that GenAI chatbots varying in tone formality and cultural tailoring significantly influence perceptions of their friendliness and credibility, which, in turn, relate to hurricane preparedness outcomes. These results highlight the potential of using GenAI chatbots to improve diverse communities' disaster preparedness.

Xinyan Zhao, Bin He, Yasheng Wang et al.

With the advances in deep learning, tremendous progress has been made with chit-chat dialogue systems and task-oriented dialogue systems. However, these two systems are often tackled separately in current methods. To achieve more natural interaction with humans, a dialogue agent needs to be capable of both chatting and accomplishing tasks. To this end, we propose a unified dialogue system (UniDS) with the two aforementioned skills. In particular, we design a unified dialogue data schema, compatible for both chit-chat and task-oriented dialogues, and we train UniDS with mixed dialogue data from a pretrained chit-chat dialogue model. Without adding extra parameters to SOTA baselines, UniDS can alternatively handle chit-chat and task-oriented dialogues in a unified framework. Experimental results demonstrate that the proposed UniDS works comparably well as the pure chit-chat system, and it outperforms state-of-the-art task-oriented dialogue systems. More importantly, UniDS achieves better robustness as it is able to smoothly switch between two types of dialogues. These results demonstrate the feasibility and potential of building an one-for-all dialogue system.

Xinyan Zhao, Haibo Ding, Zhe Feng

Instead of using expensive manual annotations, researchers have proposed to train named entity recognition (NER) systems using heuristic labeling rules. However, devising labeling rules is challenging because it often requires a considerable amount of manual effort and domain expertise. To alleviate this problem, we propose \textsc{GLaRA}, a graph-based labeling rule augmentation framework, to learn new labeling rules from unlabeled data. We first create a graph with nodes representing candidate rules extracted from unlabeled data. Then, we design a new graph neural network to augment labeling rules by exploring the semantic relations between rules. We finally apply the augmented rules on unlabeled data to generate weak labels and train a NER model using the weakly labeled data. We evaluate our method on three NER datasets and find that we can achieve an average improvement of +20\% F1 score over the best baseline when given a small set of seed rules.

Jiele Wu, Chau-Wai Wong, Xinyan Zhao et al.

Many computer scientists use the aggregated answers of online workers to represent ground truth. Prior work has shown that aggregation methods such as majority voting are effective for measuring relatively objective features. For subjective features such as semantic connotation, online workers, known for optimizing their hourly earnings, tend to deteriorate in the quality of their responses as they work longer. In this paper, we aim to address this issue by proposing a quality-aware semantic data annotation system. We observe that with timely feedback on workers' performance quantified by quality scores, better informed online workers can maintain the quality of their labeling throughout an extended period of time. We validate the effectiveness of the proposed annotation system through i) evaluating performance based on an expert-labeled dataset, and ii) demonstrating machine learning tasks that can lead to consistent learning behavior with 70%-80% accuracy. Our results suggest that with our system, researchers can collect high-quality answers of subjective semantic features at a large scale.

Xinyan Zhao, Liangwei Chen, Huanhuan Chen

Knowledge based dialogue systems have attracted increasing research interest in diverse applications. However, for disease diagnosis, the widely used knowledge graph is hard to represent the symptom-symptom relations and symptom-disease relations since the edges of traditional knowledge graph are unweighted. Most research on disease diagnosis dialogue systems highly rely on data-driven methods and statistical features, lacking profound comprehension of symptom-disease relations and symptom-symptom relations. To tackle this issue, this work presents a weighted heterogeneous graph based dialogue system for disease diagnosis. Specifically, we build a weighted heterogeneous graph based on symptom co-occurrence and a proposed symptom frequency-inverse disease frequency. Then this work proposes a graph based deep Q-network (Graph-DQN) for dialogue management. By combining Graph Convolutional Network (GCN) with DQN to learn the embeddings of diseases and symptoms from both the structural and attribute information in the weighted heterogeneous graph, Graph-DQN could capture the symptom-disease relations and symptom-symptom relations better. Experimental results show that the proposed dialogue system rivals the state-of-the-art models. More importantly, the proposed dialogue system can complete the task with less dialogue turns and possess a better distinguishing capability on diseases with similar symptoms.

Xinyan Zhao, Xiao Feng, Haoming Zhong et al.

The study of question answering has received increasing attention in recent years. This work focuses on providing an answer that compatible with both user intent and conditioning information corresponding to the question, such as delivery status and stock information in e-commerce. However, these conditions may be wrong or incomplete in real-world applications. Although existing question answering systems have considered the external information, such as categorical attributes and triples in knowledge base, they all assume that the external information is correct and complete. To alleviate the effect of defective condition values, this paper proposes condition aware and revise Transformer (CAR-Transformer). CAR-Transformer (1) revises each condition value based on the whole conversation and original conditions values, and (2) it encodes the revised conditions and utilizes the conditions embedding to select an answer. Experimental results on a real-world customer service dataset demonstrate that the CAR-Transformer can still select an appropriate reply when conditions corresponding to the question exist wrong or missing values, and substantially outperforms baseline models on automatic and human evaluations. The proposed CAR-Transformer can be extended to other NLP tasks which need to consider conditioning information.

Jie Wang, Xinyan Zhao

With rapid development of neural networks, deep-learning has been extended to various natural language generation fields, such as machine translation, dialogue generation and even literature creation. In this paper, we propose a theme-aware language generation model for Chinese music lyrics, which improves the theme-connectivity and coherence of generated paragraphs greatly. A multi-channel sequence-to-sequence (seq2seq) model encodes themes and previous sentences as global and local contextual information. Moreover, attention mechanism is incorporated for sequence decoding, enabling to fuse context into predicted next texts. To prepare appropriate train corpus, LDA (Latent Dirichlet Allocation) is applied for theme extraction. Generated lyrics is grammatically correct and semantically coherent with selected themes, which offers a valuable modelling method in other fields including multi-turn chatbots, long paragraph generation and etc.