Natural Language Processing
Natural Language Processing (NLP) research at Google focuses on algorithms that apply at scale, across languages, and across domains. Our systems are used in numerous ways across Google, impacting user experience in search, mobile, apps, ads, translate and more.
Our work spans the range of traditional NLP tasks, with general-purpose syntax and semantic algorithms underpinning more specialized systems. We are particularly interested in algorithms that scale well and can be run efficiently in a highly distributed environment.
Our syntactic systems predict part-of-speech tags for each word in a given sentence, as well as morphological features such as gender and number. They also label relationships between words, such as subject, object, modification, and others. We focus on efficient algorithms that leverage large amounts of unlabeled data, and recently have incorporated neural net technology.
On the semantic side, we identify entities in free text, label them with types (such as person, location, or organization), cluster mentions of those entities within and across documents (coreference resolution), and resolve the entities to the Knowledge Graph.
Recent work has focused on incorporating multiple sources of knowledge and information to aid with analysis of text, as well as applying frame semantics at the noun phrase, sentence, and document level.
Recent Publications
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
ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients"
Kohei Uehara
Haoyu Zhang
Jingtao Zhou
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
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
Inside-Out: Hidden Factual Knowledge in LLMs
Eran Ofek
Hadas Orgad
Zorik Gekhman
Roi Reichart
Yonatan Belinkov
Eyal Ben-David
2025
Preview abstract
This work presents a framework for assessing whether large language models (LLMs) encode more factual knowledge in their parameters than what they express
in their outputs. While a few studies hint at this possibility, none has clearly defined or demonstrated this phenomenon. We first propose a formal definition of knowledge, quantifying it for a given question as the fraction of correct-incorrect answer pairs where the correct one is ranked higher. This gives rise to external and internal knowledge, depending on the information used to score individual answer candidates: either the model’s observable token-level probabilities or its intermediate computations. Hidden knowledge arises when internal knowledge exceeds external knowledge. We then present a case study, applying this framework to three popular open-weights LLMs in a closed-book QA setup. Our results indicate that: (1) LLMs consistently encode more factual knowledge internally than what they express externally, with an average gap of 40%. (2) Surprisingly, some knowledge is so deeply hidden that a model can internally know an answer perfectly, yet fail to generate it even once, despite large-scale repeated sampling of 1,000 answers. This reveals fundamental limitations in the generation capabilities of LLMs, which (3) puts a practical constraint on scaling test-time compute via repeated answer sampling in closed-book QA: significant performance improvements remain inaccessible because some answers are practically never sampled, yet if they were, we would be guaranteed to rank them first.
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
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
×
![]()