Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 1132 publications
ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients"
Kohei Uehara
Haoyu Zhang
Lin Gu
Zheng Xu
Tatsuya Harada
ACL 2026 (2026)
Preview abstract
Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like depth-first search (DFS). This leads to inevitable annotation failures and low efficiency in data generation. We introduce ToolGrad, an agentic framework that inverts this paradigm. ToolGrad first constructs valid tool-use chains through an iterative process guided by textual "gradients", and then synthesizes corresponding user queries. This "answer-first" approach led to ToolGrad-500, a dataset generated with more complex tool use, lower cost, and almost 100% pass rate. Experiments show that ToolGrad models outperform those trained on expensive baseline datasets and proprietary LLMs.
View details
See2Refine: Vision-Language Feedback Improves LLM-Based eHMI Action Designers
Ding Xia
Xinyue Gui
Mark Colley
Fan Gao
Dongyuan Li
Renhe Jiang
Takeo Igarashi
ACL 26 (2026)
Preview abstract
Automated vehicles lack natural communication channels with other road users, making external Human-Machine Interfaces (eHMIs) essential for conveying intent and maintaining trust in shared environments. However, most eHMI studies rely on developer-crafted message-action pairs, which are difficult to adapt to diverse and dynamic traffic contexts. A promising alternative is to use Large Language Models (LLMs) as action designers that generate context-conditioned eHMI actions, yet such designers lack perceptual verification and typically depend on fixed prompts or costly human-annotated feedback for improvement. We present See2Refine, a human-free, closed-loop framework that uses vision-language models (VLMs) for perceptual evaluation as automated visual feedback to improve an LLM-based eHMI action designer. Given a driving context and a candidate eHMI action, the VLM evaluates the perceived appropriateness of the action, and this feedback is used to iteratively revise the designer's outputs, enabling systematic refinement without human supervision. We evaluate our framework across three eHMI modalities (lightbar, eyes, and arm) and multiple LLM model sizes. Across settings, our framework consistently outperforms prompt-only LLM designers and manually specified baselines in both VLM-based metrics and human-subject evaluations. Results further indicate that the improvements generalize across modalities and that VLM evaluations are well aligned with human preferences, supporting the robustness and effectiveness of \systemName for scalable action design.
View details
Preview abstract
While the Latin script is used informally by speakers of many languages with more complex native scripts, high quality Latin script corpora for such languages that reflect actual natural romanizations are scarce and often difficult to collect. In this work, we propose a method for mining romanized language corpora in languages for which we do not have any pre-existing samples of naturally romanized text, focusing on Tigrinya as a test case. First we examine the efficacy of learning romanizations for a language based on observed romanizations in other languages that use the same native script. We then extrinsically assess such methods by using a romanization model trained on Amharic data to bootstrap coverage of romanized Tigrinya in a language identification system. Manual evaluation by two L1 and one L2 Tigrinya speakers suggests our method extracts romanized Tigrinya text with acceptably high precision. We release code to run our mining pipeline on public web corpora, such as MADLAD-400.
View details
TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems
MD ATIK AHAMED
Qiang Cheng
Forty-third International Conference on Machine Learning (2026)
Preview abstract
Time-series forecasting has traditionally been evaluated solely on numerical accuracy, treating models as "black boxes'' that fail to capture the underlying reasoning. To address this gap, we introduce TFRBench, a novel benchmark designed to evaluate the reasoning capabilities of forecasting systems alongside their numerical accuracy. Unlike existing benchmarks, TFRBench requires models to generate verifiable natural language reasoning by analyzing cross-channel dependencies, identifying strategic trends, and justifying significant events using external context. To construct this benchmark, we propose a systematic multi-agent framework comprising Reasoning, Search, Verifier, Forecasting, and Summary agents. Our benchmark spans five diverse domains including Energy, Sales, Web/CloudOps, Transportation, and Finance, covering 10 distinct datasets. Qualitative evaluation confirms that our generated reasoning is highly faithful and effective; specifically, Large Language Models (LLMs) prompted with our generated reasoning demonstrate significantly improved forecasting accuracy compared to direct forecasting with LLMs. Conversely, benchmarking experiments reveal that off-the-shelf LLMs consistently struggle with both reasoning (shows lower LLM-as-Judge scores) and direct numerical forecasting (MAE and MASE), frequently failing to capture domain-specific dynamics. TFRBench thus establishes a new standard for interpretable, reasoning-based evaluation in time-series forecasting.
View details
Toward expert-level medical question answering with large language models
Karan Singhal
Juro Gottweis
Le Hou
Kevin Clark
Heather Cole-Lewis
Amy Wang
Sami Lachgar
Philip Mansfield
Sushant Prakash
Bradley Green
Ewa Dominowska
Nenad Tomašev
Renee Wong
Sara Mahdavi
Joelle Barral
Nature Medicine (2025)
Preview abstract
Large language models (LLMs) have shown promise in medical question answering, with Med-PaLM being the first to exceed a ‘passing’ score in United States Medical Licensing Examination style questions. However, challenges remain in long-form medical question answering and handling real-world workflows. Here, we present Med-PaLM 2, which bridges these gaps with a combination of base LLM improvements, medical domain fine-tuning and new strategies for improving reasoning and grounding through ensemble refinement and chain of retrieval. Med-PaLM 2 scores up to 86.5% on the MedQA dataset, improving upon Med-PaLM by over 19%, and demonstrates dramatic performance increases across MedMCQA, PubMedQA and MMLU clinical topics datasets. Our detailed human evaluations framework shows that physicians prefer Med-PaLM 2 answers to those from other physicians on eight of nine clinical axes. Med-PaLM 2 also demonstrates significant improvements over its predecessor across all evaluation metrics, particularly on new adversarial datasets designed to probe LLM limitations (P < 0.001). In a pilot study using real-world medical questions, specialists preferred Med-PaLM 2 answers to generalist physician answers 65% of the time. While specialist answers were still preferred overall, both specialists and generalists rated Med-PaLM 2 to be as safe as physician answers, demonstrating its growing potential in real-world medical applications.
View details
Towards conversational diagnostic artificial intelligence
Khaled Saab
Jan Freyberg
Ryutaro Tanno
Amy Wang
Brenna Li
Nenad Tomašev
Karan Singhal
Yong Cheng
Le Hou
Albert Webson
Kavita Kulkarni
Sara Mahdavi
Juro Gottweis
Joelle Barral
Kat Chou
Nature (2025)
Preview abstract
At the heart of medicine lies physician–patient dialogue, where skillful history-taking enables effective diagnosis, management and enduring trust. Artificial intelligence (AI) systems capable of diagnostic dialogue could increase accessibility and quality of care. However, approximating clinicians’ expertise is an outstanding challenge. Here we introduce AMIE (Articulate Medical Intelligence Explorer), a large language model (LLM)-based AI system optimized for diagnostic dialogue. AMIE uses a self-play-based simulated environment with automated feedback for scaling learning across disease conditions, specialties and contexts. We designed a framework for evaluating clinically meaningful axes of performance, including history-taking, diagnostic accuracy, management, communication skills and empathy. We compared AMIE’s performance to that of primary care physicians in a randomized, double-blind crossover study of text-based consultations with validated patient-actors similar to objective structured clinical examination. The study included 159 case scenarios from providers in Canada, the United Kingdom and India, 20 primary care physicians compared to AMIE, and evaluations by specialist physicians and patient-actors. AMIE demonstrated greater diagnostic accuracy and superior performance on 30 out of 32 axes according to the specialist physicians and 25 out of 26 axes according to the patient-actors. Our research has several limitations and should be interpreted with caution. Clinicians used synchronous text chat, which permits large-scale LLM–patient interactions, but this is unfamiliar in clinical practice. While further research is required before AMIE could be translated to real-world settings, the results represent a milestone towards conversational diagnostic AI.
View details
Towards accurate differential diagnosis with large language models
Daniel McDuff
Amy Wang
Karan Singhal
Yash Sharma
Kavita Kulkarni
Le Hou
Yong Cheng
Sara Mahdavi
Sushant Prakash
Anupam Pathak
Shwetak Patel
Ewa Dominowska
Juro Gottweis
Joelle Barral
Kat Chou
Jake Sunshine
Nature (2025)
Preview abstract
A comprehensive differential diagnosis is a cornerstone of medical care that is often reached through an iterative process of interpretation that combines clinical history, physical examination, investigations and procedures. Interactive interfaces powered by large language models present new opportunities to assist and automate aspects of this process. Here we introduce the Articulate Medical Intelligence Explorer (AMIE), a large language model that is optimized for diagnostic reasoning, and evaluate its ability to generate a differential diagnosis alone or as an aid to clinicians. Twenty clinicians evaluated 302 challenging, real-world medical cases sourced from published case reports. Each case report was read by two clinicians, who were randomized to one of two assistive conditions: assistance from search engines and standard medical resources; or assistance from AMIE in addition to these tools. All clinicians provided a baseline, unassisted differential diagnosis prior to using the respective assistive tools. AMIE exhibited standalone performance that exceeded that of unassisted clinicians (top-10 accuracy 59.1% versus 33.6%, P = 0.04). Comparing the two assisted study arms, the differential diagnosis quality score was higher for clinicians assisted by AMIE (top-10 accuracy 51.7%) compared with clinicians without its assistance (36.1%; McNemar’s test: 45.7, P < 0.01) and clinicians with search (44.4%; McNemar’s test: 4.75, P = 0.03). Further, clinicians assisted by AMIE arrived at more comprehensive differential lists than those without assistance from AMIE. Our study suggests that AMIE has potential to improve clinicians’ diagnostic reasoning and accuracy in challenging cases, meriting further real-world evaluation for its ability to empower physicians and widen patients’ access to specialist-level expertise.
View details
Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
Hailey Joren
Jianyi Zhang
Chun-Sung Ferng
Ankur Taly
International Conference on Learning Representations (ICLR) (2025)
Preview abstract
Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whether errors arise because LLMs fail to utilize the context from retrieval or the context itself is insufficient to answer the query. To shed light on this, we develop a new notion of sufficient context, along with a method to classify instances that have enough information to answer the query. We then use sufficient context to analyze several models and datasets. By stratifying errors based on context sufficiency, we find that larger models with higher baseline performance (Gemini 1.5 Pro, GPT 4o, Claude 3.5) excel at answering queries when the context is sufficient, but often output incorrect answers instead of abstaining when the context is not. On the other hand, smaller models with lower baseline performance (Llama 3.1, Mistral 3, Gemma 2) hallucinate or abstain often, even with sufficient context. We further categorize cases when the context is useful, and improves accuracy, even though it does not fully answer the query and the model errs without the context. Building on our findings, we explore ways to reduce hallucinations in RAG systems, including a new selective generation method that leverages sufficient context information for guided abstention. Our method improves the fraction of correct answers among times where the model responds by 2--10% for Gemini, GPT, and Gemma.
View details
Preview abstract
Large-scale video generative models, capable of creating realistic videos of diverse visual concepts, are strong candidates for general-purpose physical world simulators. However, their adherence to physical commonsense across real-world actions remains unclear (e.g., playing tennis, backflip). Existing benchmarks suffer from limitations such as limited size, lack of human evaluation, sim-to-real gaps, and absence of fine-grained physical rule analysis. To address this, we introduce VideoPhy-2, an action-centric dataset for evaluating physical commonsense in generated videos. We curate 200 diverse actions and detailed prompts for video synthesis from modern generative models. We perform human evaluation that assesses semantic adherence, physical commonsense, and grounding of physical rules in the generated videos. Our findings reveal major shortcomings, with even the best model achieving only 22% joint performance (i.e., high semantic and physical commonsense adherence) on the hard subset of VideoPhy-2. We find that the models particularly struggle with conservation laws like mass and momentum. Finally, we also train VideoPhy-AutoEval, an automatic evaluator for fast, reliable assessment on our dataset. Overall, VideoPhy-2 serves as a rigorous benchmark, exposing critical gaps in video generative models and guiding future research in physically-grounded video generation. The data and code is available at https://videophy2.github.io/
View details
RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation
Aviv Slobodkin
Hagai Taitelbaum
Brian Gordon
Michal Sokolik
Almog Gueta
Royi Rassin
Dani Lischinski
2025
Preview abstract
Subject-driven text-to-image (T2I) generation aims to produce images that align with a given textual description, while preserving the visual identity from a referenced subject image. Despite its broad downstream applicability - ranging from enhanced personalization in image generation to consistent character representation in video rendering - progress in this field is limited by the lack of reliable automatic evaluation. Existing methods either assess only one aspect of the task (i.e., textual alignment or subject preservation), misalign with human judgments, or rely on costly API-based evaluation. To address this gap, we introduce RefVNLI, a cost-effective metric that evaluates both textual alignment and subject preservation in a single run. Trained on a large-scale dataset derived from video-reasoning benchmarks and image perturbations, RefVNLI outperforms or statistically matches existing baselines across multiple benchmarks and subject categories (e.g., Animal, Object), achieving up to 6.4-point gains in textual alignment and 5.9-point gains in subject preservation.
View details
Improving Informally Romanized Language Identification
Adrian Benton
Christo Kirov
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, Suzhou, China, 2318–2336
Preview abstract
The Latin script is often used informally to write languages with non-Latin native scripts. In many cases (e.g., most languages in India), there is no orthography, meaning that there is no conventional spelling of words in the Latin script, hence there will be high spelling variability in written text. Such romanization can render languages that are normally easily distinguished based on script highly confusable, such as Hindi and Urdu. In this work, we present methods to improve language identification of romanized text by improving methods to synthesize training sets. We find that training on synthetic samples which incorporate natural spelling variation yields higher language identification system accuracy than including available naturally occurring examples in the training set or even training higher capacity models. We demonstrate new state-of-the-art language identification performance on romanized text from 20 Indic languages in the Bhasha-Abhijnaanam evaluation set (Madhani et al., 2023a), improving test F1 from the reported 74.7% (using a pretrained neural model) to 85.4% using a linear classifier trained solely on synthetic data and 88.2% when also training on available harvested text.
View details
VaultGemma
Lynn Chua
Prem Eruvbetine
Chiyuan Zhang
Thomas Mesnard
Borja De Balle Pigem
Daogao Liu
Amer Sinha
Pritish Kamath
Yangsibo Huang
Christopher A. Choquette-Choo
George Kaissis
Armand Joulin
Andreas Terzis
Da Yu
Ryan McKenna
Ruibo Liu
arxiv (2025)
Preview abstract
In this work, we present VaultGemma 1B, a model based on the Gemma family of models fully trained with differential privacy. VaultGemma 1B is 1 billion parameter pretrained model based on the Gemma 2 series of models and uses the same dataset for training. We will be releasing a tech report and the weights of this model.
View details
Analyzing Similarity Metrics for Data Selection for Language Model Pretraining
Dylan Sam
Afshin Rostamizadeh
Gui Citovsky
Advances in Neural Information Processing Systems (NeurIPS) (2025) (to appear)
Preview abstract
Measuring similarity between training examples is critical for curating high-quality and diverse pretraining datasets for language models. However, similarity is typically computed with a generic off-the-shelf embedding model that has been trained for tasks such as retrieval. Whether these embedding-based similarity metrics are well-suited for pretraining data selection remains largely unexplored. In this paper, we propose a new framework to assess the suitability of a similarity metric specifically for data curation in language model pretraining applications. Our framework's first evaluation criterion captures how well distances reflect generalization in pretraining loss between different training examples. Next, we use each embedding model to guide a standard diversity-based data curation algorithm and measure its utility by pretraining a language model on the selected data and evaluating downstream task performance. Finally, we evaluate the capabilities of embeddings to distinguish between examples from different data sources. With these evaluations, we demonstrate that standard off-the-shelf embedding models are not well-suited for the pretraining data curation setting, underperforming even remarkably simple embeddings that are extracted from models trained on the same pretraining corpus. Our experiments are performed on the Pile, for pretraining a 1.7B parameter language model on 200B tokens. We believe our analysis and evaluation framework serves as a foundation for the future design of embeddings that specifically reason about similarity in pretraining datasets.
View details
Preview abstract
A critical component in the trustworthiness of LLMs is reliable uncertainty communication, yet LLMs often use assertive language when conveying false claims, leading to over-reliance and eroded trust. We present the first systematic study of faithful confidence calibration of LLMs, benchmarking models' ability to use linguistic expressions of uncertainty that faithfully reflect their intrinsic uncertainty, across a comprehensive array of models, datasets, and prompting strategies. Our results demonstrate that LLMs largely fail at this task, and that existing interventions are insufficient: standard prompt approaches provide only marginal gains, and existing, factuality-based calibration techniques can even harm faithful calibration. To address this critical gap, we introduce MetaFaith, a novel prompt-based calibration approach inspired by human metacognition. We show that MetaFaith robustly improves faithful calibration across diverse models and task domains, enabling up to 61% improvement in faithfulness and achieving an 83% win rate over original generations as judged by humans.
View details
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
Lei Li
Wenda Xu
Rishabh Agarwal
William Wang
Dhruv Madeka
ICLR 2025
Preview abstract
Recent knowledge distillation (KD) research made significant progress on improving smaller student models to match larger teachers' performances. Two noticeable methods, supervised KD and on-policy KD emerged as the state-of-the-art approaches. However, supervised KD for auto-regressive models suffers from distribution mismatch between training over fixed dataset and inference over student generated outputs. Conversely, on-policy KD, which uses student-generated samples for training, can suffer from low-quality training examples and the teacher's potential inaccuracies in assessing these samples. To address these limitations, we introduce Speculative Knowledge Distillation (SKD). Instead of solely training on teacher- or student-proposed samples, SKD leverages the student model to initially propose tokens following its own generation distribution. Subsequently, the teacher model is employed to replace tokens that are deemed out-of-distribution. Compared with supervised KD, the samples generated by SKD are more likely to align with the student's inference-time distribution, and 2) SKD can mitigate the generation of low-quality sequences by incorporating the teacher's feedback at each token. Furthermore, we demonstrate that SKD is a generic framework capable of implementing both supervised and on-policy knowledge distillation as specific instances. To validate SKD's effectiveness, we apply it to distill autoregressive large language models for various tasks, including translation, summarization, math, and instruction following. Our experiments consistently demonstrate SKD's superior performance compared to existing methods across different domains, tasks, data sizes, and model initialization strategies.
View details
