Mert Yuksekgonul

All Publications

• Optimizing generative AI by backpropagating language model feedback. Nature Yuksekgonul, M., Bianchi, F., Boen, J., Liu, S., Lu, P., Huang, Z., Guestrin, C., Zou, J. 2025; 639 (8055): 609-616

  Abstract

  Recent breakthroughs in artificial intelligence (AI) are increasingly driven by systems orchestrating multiple large language models (LLMs) and other specialized tools, such as search engines and simulators. So far, these systems are primarily handcrafted by domain experts and tweaked through heuristics rather than being automatically optimized, presenting a substantial challenge to accelerating progress. The development of artificial neural networks faced a similar challenge until backpropagation and automatic differentiation transformed the field by making optimization turnkey. Analogously, here we introduce TextGrad, a versatile framework that performs optimization by backpropagating LLM-generated feedback to improve AI systems. By leveraging natural language feedback to critique and suggest improvements to any part of a system-from prompts to outputs such as molecules or treatment plans-TextGrad enables the automatic optimization of generative AI systems across diverse tasks. We demonstrate TextGrad's generality and effectiveness through studies in solving PhD-level science problems, optimizing plans for radiotherapy treatments, designing molecules with specific properties, coding, and optimizing agentic systems. TextGrad empowers scientists and engineers to easily develop impactful generative AI systems.

  View details for DOI 10.1038/s41586-025-08661-4

  View details for PubMedID 40108317

  View details for PubMedCentralID 10794143

• How Well Can LLMs Negotiate? NEGOTIATIONARENA Platform and Analysis Bianchi, F., Chia, P., Yuksekgonul, M., Tagliabue, J., Jurafsky, D., Zou, J., Salakhutdinov, R., Kolter, Z., Heller, K., Weller, A., Oliver, N., Scarlett, J., Berkenkamp, F. JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2024

  View details for Web of Science ID 001347135504002

• A visual-language foundation model for pathology image analysis using medical Twitter. Nature medicine Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T. J., Zou, J. 2023

  Abstract

  The lack of annotated publicly available medical images is a major barrier for computational research and education innovations. At the same time, many de-identified images and much knowledge are shared by clinicians on public forums such as medical Twitter. Here we harness these crowd platforms to curate OpenPath, a large dataset of 208,414 pathology images paired with natural language descriptions. We demonstrate the value of this resource by developing pathology language-image pretraining (PLIP), a multimodal artificial intelligence with both image and text understanding, which is trained on OpenPath. PLIP achieves state-of-the-art performances for classifying new pathology images across four external datasets: for zero-shot classification, PLIP achieves F1 scores of 0.565-0.832 compared to F1 scores of 0.030-0.481 for previous contrastive language-image pretrained model. Training a simple supervised classifier on top of PLIP embeddings also achieves 2.5% improvement in F1 scores compared to using other supervised model embeddings. Moreover, PLIP enables users to retrieve similar cases by either image or natural language search, greatly facilitating knowledge sharing. Our approach demonstrates that publicly shared medical information is a tremendous resource that can be harnessed to develop medical artificial intelligence for enhancing diagnosis, knowledge sharing and education.

  View details for DOI 10.1038/s41591-023-02504-3

  View details for PubMedID 37592105

  View details for PubMedCentralID 9883475

• GPT detectors are biased against non-native English writers. Patterns (New York, N.Y.) Liang, W., Yuksekgonul, M., Mao, Y., Wu, E., Zou, J. 2023; 4 (7): 100779

  Abstract

  GPT detectors frequently misclassify non-native English writing as AI generated, raising concerns about fairness and robustness. Addressing the biases in these detectors is crucial to prevent the marginalization of non-native English speakers in evaluative and educational settings and to create a more equitable digital landscape.

  View details for DOI 10.1016/j.patter.2023.100779

  View details for PubMedID 37521038

• Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanations Abid, A., Yuksekgonul, M., Zou, J., Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2022: 66-88

  View details for Web of Science ID 000899944900005