arXiv subjects

Mark Yatskar

Publications and source records attributed to Mark Yatskar.

At least 19 recordsLinked to original sources

arXiv2026

Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale

Manually curated biomedical repositories -- spanning bioactivity, genomics, and chemistry -- are expensive to maintain, lag behind primary literature, and discard experimental context, obscuring nuances needed to assess data correctness and coverage. We show that PubMed itself can be autonomously and cost-effectively turned into structured datasets that are larger, more nuanced, and more accurate than the curated databases they replace. We present three coupled contributions: (1) an LLM-based entity-tagging pipeline, grounded in nine biomedical ontologies, that tags 4.5B entities across 19 categories in a 22.5M-paper, 2.5T-token PubMed corpus; (2) hybrid sparse-dense retrieval supporting entity-filtered semantic queries over the tagged corpus; and (3) Starling, a multi-agent deep research system that, given only a natural-language task description, designs precision- and recall-targeted retrieval filters, induces an extraction schema, and emits structured records with nuance-rich fields and supporting passages. Across six tasks -- blood-brain barrier permeability, oral bioavailability, acute toxicity (LD50), gene-disease associations, protein subcellular localization, and chemical reactions -- Starling produces ~6.3M records (91K-3M per task); several are, to our knowledge, the largest public datasets for their property. Frontier-model rejection of our extractions is 0.6-7.7% across tasks, far below error rates we measure on widely used curated counterparts (e.g., 16.5% on BBB_Martins, 7.3% on Bioavailability_Ma). Beyond scale and accuracy, the supporting passages carry nuance tabular databases discard -- e.g., oral bioavailability may depend on fed vs. fasted state. Together, the corpus, retrieval, and agent establish a foundation for AI-driven therapeutic design. Code and datasets: https://github.com/starling-labs/starling.

cs.LG↗

arXiv2026

Purely Agent-Driven Black-Box Optimization for Biological Design

Many key challenges in biological design -- such as small-molecule drug discovery, antimicrobial peptide development, and protein engineering -- can be framed as black-box optimization over vast, complex structured spaces. Existing methods rely mainly on raw structural data and struggle to exploit the rich scientific literature. While large language models (LLMs) have been added to these pipelines, they have been confined to narrow roles within structure-centered optimizers. We instead cast biological black-box optimization as an agent-driven, language-based reasoning process. We introduce Purely Agent-driven BLack-box Optimization (PABLO), a hierarchical agentic system that uses scientific LLMs pretrained on chemistry and biology literature to generate and iteratively refine biological candidates. On both the standard GuacaMol molecular design and antimicrobial peptide optimization tasks, PABLO achieves state-of-the-art performance, substantially improving sample efficiency and final objective values over established baselines. Compared to prior optimization methods that incorporate LLMs, PABLO achieves competitive token usage per run despite relying on LLMs throughout the optimization loop. Beyond raw performance, the agentic formulation offers key advantages for realistic design: it naturally incorporates semantic task descriptions, retrieval-augmented domain knowledge, and complex constraints. In follow-up in vitro validation, PABLO-optimized peptides showed strong activity against drug-resistant pathogens, underscoring the practical potential of PABLO for therapeutic discovery.

cs.LG↗

arXiv2025

ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics

Evaluating long-form responses to research queries heavily relies on expert annotators, restricting attention to areas like AI where researchers can conveniently enlist colleagues. Yet, research expertise is abundant: survey articles consolidate knowledge spread across the literature. We introduce ResearchQA, a resource for evaluating LLM systems by distilling survey articles from 75 research fields into 21K queries and 160K rubric items. Queries and rubrics are jointly derived from survey sections, where rubric items list query-specific answer evaluation criteria, i.e., citing papers, making explanations, and describing limitations. 31 Ph.D. annotators in 8 fields judge that 90% of queries reflect Ph.D. information needs and 87% of rubric items warrant emphasis of a sentence or longer. We leverage ResearchQA to evaluate 18 systems in 7.6K head-to-heads. No parametric or retrieval-augmented system we evaluate exceeds 70% on covering rubric items, and the highest-ranking system shows 75% coverage. Error analysis reveals that the highest-ranking system fully addresses less than 11% of citation rubric items, 48% of limitation items, and 49% of comparison items. We release our data to facilitate more comprehensive multi-field evaluations.

cs.CL↗

arXiv2025

A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design

AI-driven discovery can greatly reduce design time and enhance new therapeutics' effectiveness. Models using simulators explore broad design spaces but risk violating implicit constraints due to a lack of experimental priors. For example, in a new analysis we performed on a diverse set of models on the GuacaMol benchmark using supervised classifiers, over 60\% of molecules proposed had high probability of being mutagenic. In this work, we introduce Medex, a dataset of priors for design problems extracted from literature describing compounds used in lab settings. It is constructed with LLM pipelines for discovering therapeutic entities in relevant paragraphs and summarizing information in concise fair-use facts. Medex consists of 32.3 million pairs of natural language facts, and appropriate entity representations (i.e. SMILES or refseq IDs). To demonstrate the potential of the data, we train LLM, CLIP, and LLava architectures to reason jointly about text and design targets and evaluate on tasks from the Therapeutic Data Commons (TDC). Medex is highly effective for creating models with strong priors: in supervised prediction problems that use our data as pretraining, our best models with 15M learnable parameters outperform larger 2B TxGemma on both regression and classification TDC tasks, and perform comparably to 9B models on average. Models built with Medex can be used as constraints while optimizing for novel molecules in GuacaMol, resulting in proposals that are safer and nearly as effective. We release our dataset at https://huggingface.co/datasets/medexanon/Medex, and will provide expanded versions as available literature grows.

cs.LG↗

arXiv2025

Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models

Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over substantive qualities. This bias manifests as overreliance on features like length, structure, and style, leading to issues like reward hacking and unreliable evaluations. However, the connection between training data artifacts and the miscalibrated preferences exhibited by models remains poorly understood. In this work, we systematically investigate the relationship between training data biases and preference model miscalibration across five idiosyncratic features of language model generations: length, structure, jargon, sycophancy and vagueness. Using controlled counterfactual pairs, we first quantify the extent to which preference models favor responses with artificially magnified biases (skew), finding this preference occurs in $>60\%$ of instances, and model preferences show high miscalibration ($\approx 40\%$) compared to human preferences. Notably, bias features only show mild negative correlations to human preference labels (mean $r_{\mathrm{human}} = -0.12$) but show moderately strong positive correlations with labels from a strong reward model (mean $r_{\mathrm{model}} = +0.36$), suggesting that models may overrely on spurious cues. To mitigate these issues, we propose a simple post-training method based on counterfactual data augmentation (CDA) using synthesized contrastive examples. Fine-tuning models with CDA reduces average miscalibration from $39.4\%$ to $32.5\%$ and average absolute skew difference from $20.5\%$ to $10.0\%$, while maintaining overall RewardBench performance, indicating that targeted debiasing can strengthen the reliability of preference models within standard alignment pipelines.

cs.CL↗

arXiv2025

Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D

Real-world decision-making often begins with identifying which modality contains the most relevant information for a given query. While recent multimodal models have made impressive progress in processing diverse inputs, it remains unclear whether they can reason contrastively across multiple modalities to select the one that best satisfies a natural language prompt. We argue this capability is foundational, especially in retrieval-augmented and decision-time contexts, where systems must evaluate multiple signals and identify which one conveys the relevant information. To evaluate this skill, we introduce Contra4, a dataset for contrastive cross-modal reasoning across four modalities: image, audio, video, and 3D. Each example presents a natural language question alongside multiple candidate modality instances, and the model must select the one that semantically aligns with the prompt. Contra4 combines human-annotated captions with a mixture-of-models round-trip-consistency filter to ensure high-quality supervision, resulting in 174k training examples and a manually verified test set of 2.3k samples. While task-specific fine-tuning helps improve performance by 56% relative to baseline, state-of-the-art models still achieve only an absolute of 56% accuracy overall and 42% in four-modality settings, underscoring a significant limitation in current multimodal models.

cs.AI↗

arXiv2025

Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation

Reasoning about images with rich text, such as charts and documents, is a critical application of vision-language models (VLMs). However, VLMs often struggle in these domains due to the scarcity of diverse text-rich vision-language data. To address this challenge, we present CoSyn, a framework that leverages the coding capabilities of text-only large language models (LLMs) to automatically create synthetic text-rich multimodal data. Given input text describing a target domain (e.g., "nutrition fact labels"), CoSyn prompts an LLM to generate code (Python, HTML, LaTeX, etc.) for rendering synthetic images. With the underlying code as textual representations of the synthetic images, CoSyn can generate high-quality instruction-tuning data, again relying on a text-only LLM. Using CoSyn, we constructed a dataset comprising 400K images and 2.7M rows of vision-language instruction-tuning data. Comprehensive experiments on seven benchmarks demonstrate that models trained on our synthetic data achieve state-of-the-art performance among competitive open-source models, including Llama 3.2, and surpass proprietary models such as GPT-4V and Gemini 1.5 Flash. Furthermore, CoSyn can produce synthetic pointing data, enabling VLMs to ground information within input images, showcasing its potential for developing multimodal agents capable of acting in real-world environments.

cs.CV↗

arXiv2024

ViUniT: Visual Unit Tests for More Robust Visual Programming

Programming based approaches to reasoning tasks have substantially expanded the types of questions models can answer about visual scenes. Yet on benchmark visual reasoning data, when models answer correctly, they produce incorrect programs 33% of the time. These models are often right for the wrong reasons and risk unexpected failures on new data. Unit tests play a foundational role in ensuring code correctness and could be used to repair such failures. We propose Visual Unit Testing (ViUniT), a framework to improve the reliability of visual programs by automatically generating unit tests. In our framework, a unit test is represented as a novel image and answer pair meant to verify the logical correctness of a program produced for a given query. Our method leverages a language model to create unit tests in the form of image descriptions and expected answers and image synthesis to produce corresponding images. We conduct a comprehensive analysis of what constitutes an effective visual unit test suite, exploring unit test generation, sampling strategies, image generation methods, and varying the number of programs and unit tests. Additionally, we introduce four applications of visual unit tests: best program selection, answer refusal, re-prompting, and unsupervised reward formulations for reinforcement learning. Experiments with two models across three datasets in visual question answering and image-text matching demonstrate that ViUniT improves model performance by 11.4%. Notably, it enables 7B open-source models to outperform gpt-4o-mini by an average of 7.7% and reduces the occurrence of programs that are correct for the wrong reasons by 40%.

cs.CV↗

arXiv2024

Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries

Language model users often issue queries that lack specification, where the context under which a query was issued -- such as the user's identity, the query's intent, and the criteria for a response to be useful -- is not explicit. For instance, a good response to a subjective query like "What book should I read next?" would depend on the user's preferences, and a good response to an open-ended query like "How do antibiotics work against bacteria?" would depend on the user's expertise. This makes evaluation of responses to such queries an ill-posed task, as evaluators may make arbitrary judgments about the response quality. To remedy this, we present contextualized evaluations, a protocol that synthetically constructs context surrounding an underspecified query and provides it during evaluation. We find that the presence of context can 1) alter conclusions drawn from evaluation, even flipping benchmark rankings between model pairs, 2) nudge evaluators to make fewer judgments based on surface-level criteria, like style, and 3) provide new insights about model behavior across diverse contexts. Specifically, our procedure suggests a potential bias towards WEIRD (Western, Educated, Industrialized, Rich and Democratic) contexts in models' "default" responses and we find that models are not equally sensitive to following different contexts, even when they are provided in prompts.

cs.CL↗

arXiv2024

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

Today's most advanced vision-language models (VLMs) remain proprietary. The strongest open-weight models rely heavily on synthetic data from proprietary VLMs to achieve good performance, effectively distilling these closed VLMs into open ones. As a result, the community has been missing foundational knowledge about how to build performant VLMs from scratch. We present Molmo, a new family of VLMs that are state-of-the-art in their class of openness. Our key contribution is a collection of new datasets called PixMo, including a dataset of highly detailed image captions for pre-training, a free-form image Q&A dataset for fine-tuning, and an innovative 2D pointing dataset, all collected without the use of external VLMs. The success of our approach relies on careful modeling choices, a well-tuned training pipeline, and, most critically, the quality of our newly collected datasets. Our best-in-class 72B model not only outperforms others in the class of open weight and data models, but also outperforms larger proprietary models including Claude 3.5 Sonnet, and Gemini 1.5 Pro and Flash, second only to GPT-4o based on both academic benchmarks and on a large human evaluation. Our model weights, new datasets, and source code are available at https://molmo.allenai.org/blog.

cs.CV↗

arXiv2024

LLM-based Hierarchical Concept Decomposition for Interpretable Fine-Grained Image Classification

(Renyi Qu's Master's Thesis) Recent advancements in interpretable models for vision-language tasks have achieved competitive performance; however, their interpretability often suffers due to the reliance on unstructured text outputs from large language models (LLMs). This introduces randomness and compromises both transparency and reliability, which are essential for addressing safety issues in AI systems. We introduce \texttt{Hi-CoDe} (Hierarchical Concept Decomposition), a novel framework designed to enhance model interpretability through structured concept analysis. Our approach consists of two main components: (1) We use GPT-4 to decompose an input image into a structured hierarchy of visual concepts, thereby forming a visual concept tree. (2) We then employ an ensemble of simple linear classifiers that operate on concept-specific features derived from CLIP to perform classification. Our approach not only aligns with the performance of state-of-the-art models but also advances transparency by providing clear insights into the decision-making process and highlighting the importance of various concepts. This allows for a detailed analysis of potential failure modes and improves model compactness, therefore setting a new benchmark in interpretability without compromising the accuracy.

cs.CV↗

arXiv2024

A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis

While deep networks have achieved broad success in analyzing natural images, when applied to medical scans, they often fail in unexcepted situations. We investigate this challenge and focus on model sensitivity to domain shifts, such as data sampled from different hospitals or data confounded by demographic variables such as sex, race, etc, in the context of chest X-rays and skin lesion images. A key finding we show empirically is that existing visual backbones lack an appropriate prior from the architecture for reliable generalization in these settings. Taking inspiration from medical training, we propose giving deep networks a prior grounded in explicit medical knowledge communicated in natural language. To this end, we introduce Knowledge-enhanced Bottlenecks (KnoBo), a class of concept bottleneck models that incorporates knowledge priors that constrain it to reason with clinically relevant factors found in medical textbooks or PubMed. KnoBo uses retrieval-augmented language models to design an appropriate concept space paired with an automatic training procedure for recognizing the concept. We evaluate different resources of knowledge and recognition architectures on a broad range of domain shifts across 20 datasets. In our comprehensive evaluation with two imaging modalities, KnoBo outperforms fine-tuned models on confounded datasets by 32.4% on average. Finally, evaluations reveal that PubMed is a promising resource for making medical models less sensitive to domain shift, outperforming other resources on both diversity of information and final prediction performance.

cs.CV↗

arXiv2024

DOLOMITES: Domain-Specific Long-Form Methodical Tasks

Experts in various fields routinely perform methodical writing tasks to plan, organize, and report their work. From a clinician writing a differential diagnosis for a patient, to a teacher writing a lesson plan for students, these tasks are pervasive, requiring to methodically generate structured long-form output for a given input. We develop a typology of methodical tasks structured in the form of a task objective, procedure, input, and output, and introduce DoLoMiTes, a novel benchmark with specifications for 519 such tasks elicited from hundreds of experts from across 25 fields. Our benchmark further contains specific instantiations of methodical tasks with concrete input and output examples (1,857 in total) which we obtain by collecting expert revisions of up to 10 model-generated examples of each task. We use these examples to evaluate contemporary language models highlighting that automating methodical tasks is a challenging long-form generation problem, as it requires performing complex inferences, while drawing upon the given context as well as domain knowledge.

cs.CL↗

arXiv2024

Holodeck: Language Guided Generation of 3D Embodied AI Environments

3D simulated environments play a critical role in Embodied AI, but their creation requires expertise and extensive manual effort, restricting their diversity and scope. To mitigate this limitation, we present Holodeck, a system that generates 3D environments to match a user-supplied prompt fully automatedly. Holodeck can generate diverse scenes, e.g., arcades, spas, and museums, adjust the designs for styles, and can capture the semantics of complex queries such as "apartment for a researcher with a cat" and "office of a professor who is a fan of Star Wars". Holodeck leverages a large language model (i.e., GPT-4) for common sense knowledge about what the scene might look like and uses a large collection of 3D assets from Objaverse to populate the scene with diverse objects. To address the challenge of positioning objects correctly, we prompt GPT-4 to generate spatial relational constraints between objects and then optimize the layout to satisfy those constraints. Our large-scale human evaluation shows that annotators prefer Holodeck over manually designed procedural baselines in residential scenes and that Holodeck can produce high-quality outputs for diverse scene types. We also demonstrate an exciting application of Holodeck in Embodied AI, training agents to navigate in novel scenes like music rooms and daycares without human-constructed data, which is a significant step forward in developing general-purpose embodied agents.

cs.CV↗

arXiv2024

Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering

Recent advances in multimodal large language models (LLMs) have shown extreme effectiveness in visual question answering (VQA). However, the design nature of these end-to-end models prevents them from being interpretable to humans, undermining trust and applicability in critical domains. While post-hoc rationales offer certain insight into understanding model behavior, these explanations are not guaranteed to be faithful to the model. In this paper, we address these shortcomings by introducing an interpretable by design model that factors model decisions into intermediate human-legible explanations, and allows people to easily understand why a model fails or succeeds. We propose the Dynamic Clue Bottleneck Model ( (DCLUB), a method that is designed towards an inherently interpretable VQA system. DCLUB provides an explainable intermediate space before the VQA decision and is faithful from the beginning, while maintaining comparable performance to black-box systems. Given a question, DCLUB first returns a set of visual clues: natural language statements of visually salient evidence from the image, and then generates the output based solely on the visual clues. To supervise and evaluate the generation of VQA explanations within DCLUB, we collect a dataset of 1.7k reasoning-focused questions with visual clues. Evaluations show that our inherently interpretable system can improve 4.64% over a comparable black-box system in reasoning-focused questions while preserving 99.43% of performance on VQA-v2.

cs.CL↗

arXiv2024

Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck

Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically interpretable text classification framework that offers both global and local explanations. Rather than directly predicting the output label, TBM predicts categorical values for a sparse set of salient concepts and uses a linear layer over those concept values to produce the final prediction. These concepts can be automatically discovered and measured by a Large Language Model (LLM) without the need for human curation. Experiments on 12 diverse text understanding datasets demonstrate that TBM can rival the performance of black-box baselines such as few-shot GPT-4 and finetuned DeBERTa while falling short against finetuned GPT-3.5. Comprehensive human evaluation validates that TBM can generate high-quality concepts relevant to the task, and the concept measurement aligns well with human judgments, suggesting that the predictions made by TBMs are interpretable. Overall, our findings suggest that TBM is a promising new framework that enhances interpretability with minimal performance tradeoffs.

cs.CL↗

arXiv2024

ExpertQA: Expert-Curated Questions and Attributed Answers

As language models are adopted by a more sophisticated and diverse set of users, the importance of guaranteeing that they provide factually correct information supported by verifiable sources is critical across fields of study. This is especially the case for high-stakes fields, such as medicine and law, where the risk of propagating false information is high and can lead to undesirable societal consequences. Previous work studying attribution and factuality has not focused on analyzing these characteristics of language model outputs in domain-specific scenarios. In this work, we conduct human evaluation of responses from a few representative systems along various axes of attribution and factuality, by bringing domain experts in the loop. Specifically, we collect expert-curated questions from 484 participants across 32 fields of study, and then ask the same experts to evaluate generated responses to their own questions. In addition, we ask experts to improve upon responses from language models. The output of our analysis is ExpertQA, a high-quality long-form QA dataset with 2177 questions spanning 32 fields, along with verified answers and attributions for claims in the answers.

cs.CL↗

arXiv2024

What if you said that differently?: How Explanation Formats Affect Human Feedback Efficacy and User Perception

Eliciting feedback from end users of NLP models can be beneficial for improving models. However, how should we present model responses to users so they are most amenable to be corrected from user feedback? Further, what properties do users value to understand and trust responses? We answer these questions by analyzing the effect of rationales (or explanations) generated by QA models to support their answers. We specifically consider decomposed QA models that first extract an intermediate rationale based on a context and a question and then use solely this rationale to answer the question. A rationale outlines the approach followed by the model to answer the question. Our work considers various formats of these rationales that vary according to well-defined properties of interest. We sample rationales from language models using few-shot prompting for two datasets, and then perform two user studies. First, we present users with incorrect answers and corresponding rationales in various formats and ask them to provide natural language feedback to revise the rationale. We then measure the effectiveness of this feedback in patching these rationales through in-context learning. The second study evaluates how well different rationale formats enable users to understand and trust model answers, when they are correct. We find that rationale formats significantly affect how easy it is (1) for users to give feedback for rationales, and (2) for models to subsequently execute this feedback. In addition, formats with attributions to the context and in-depth reasoning significantly enhance user-reported understanding and trust of model outputs.

cs.CL↗