---
title: "James Zou — all works — Elamur Research"
description: "All 66 works of James Zou in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/james-zou/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/james-zou/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [James Zou](https://md.research.elamur.ai/free/en/authors/james-zou/) / all works

# James Zou — all works

66 works · [← James Zou](https://md.research.elamur.ai/free/en/authors/james-zou/)

1. [**Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings arXiv:1607.06520**Tolga Bolukbasi, Kai-Wei Chang, James Zou, et al.*2016 · 2,079 citations*](https://md.research.elamur.ai/free/en/papers/bolukbasi-2016-man-computer-programmer-woman-homemaker/)
2. **[Word embeddings quantify 100 years of gender and ethnic stereotypes ↗](https://doi.org/10.1073/pnas.1720347115) Proceedings of the National Academy of Sciences · no summary yet**Nikhil Garg et al.*2018 · 1,296 citations*
3. **[Interpretation of Neural Networks Is Fragile ↗](https://doi.org/10.1609/aaai.v33i01.33013681) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Amirata Ghorbani, Abubakar Abid, James Zou*2017 · 772 citations*
4. **[Persistent Anti-Muslim Bias in Large Language Models](https://md.research.elamur.ai/free/en/papers/abid-2021-persistent-anti-muslim-bias-large/) [Proceedings of the AAAI/ACM Conference on AI Ethics and Society](https://md.research.elamur.ai/free/en/venues/proceedings-of-the-aaai-acm-conference-on-ai-ethics-and-society/)**Abubakar Abid, Maheen Farooqi, James Zou*2021 · 653 citations*
5. **[Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale ↗](https://doi.org/10.1145/3593013.3594095) ACM Conference on Fairness, Accountability, and Transparency (FAccT) · no summary yet**Federico Bianchi et al.*2023 · 377 citations*
6. **[Can large language models provide useful feedback on research papers? A large-scale empirical analysis ↗](https://arxiv.org/abs/2310.01783) arXiv:2310.01783 · no summary yet**Weixin Liang et al.*2023 · 332 citations*
7. **[MOPO: Model-based Offline Policy Optimization ↗](https://arxiv.org/abs/2005.13239) arXiv (Cornell University) · no summary yet**Tianhe Yu et al.*2020 · 260 citations*
8. [**FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance arXiv:2305.05176**Lingjiao Chen, Matei Zaharia, James Zou*2023 · 241 citations*](https://md.research.elamur.ai/free/en/papers/chen-2023-frugalgpt-use-large-language-models/)
9. **[Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings ↗](https://aclanthology.org/N19-1304/) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · no summary yet**Dorottya Demszky et al.*2019 · 216 citations*
10. **[Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials ↗](https://doi.org/10.1038/s41746-022-00613-w) npj Digital Medicine · no summary yet**Andre Esteva et al.*2022 · 215 citations*
11. **[When and why vision-language models behave like bags-of-words, and what to do about it? ↗](https://arxiv.org/abs/2210.01936) arXiv (Cornell University) · no summary yet**Mert Yüksekgönül et al.*2022 · 140 citations*
12. [**Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions arXiv:2309.07875**Federico Bianchi, Mirac Suzgun, Giuseppe Attanasio, et al.*2023 · 135 citations*](https://md.research.elamur.ai/free/en/papers/bianchi-2023-safety-tuned-llamas-lessons-improving/)
13. **[Mind the Gap: Understanding the Modality Gap in Multi-Modal Contrastive Representation Learning ↗](https://doi.org/10.52202/068431-1280) neural information processing systems · no summary yet**Weixin Liang et al.*2022 · 128 citations*
14. **[Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews ↗](https://arxiv.org/abs/2403.07183) arXiv:2403.07183 · no summary yet**Weixin Liang et al.*2024 · 119 citations*
15. **[Mixture-of-Agents Enhances Large Language Model Capabilities ↗](https://arxiv.org/abs/2406.04692) arXiv:2406.04692 · no summary yet**Junlin Wang et al.*2024 · 116 citations*
16. **[Optimizing generative AI by backpropagating language model feedback ↗](https://doi.org/10.1038/s41586-025-08661-4) Nature · no summary yet**Mert Yüksekgönül et al.*2025 · 115 citations*
17. [**GPT detectors are biased against non-native English writers arXiv:2304.02819**Weixin Liang, Mert Yuksekgonul, Yining Mao, et al.*2023 · 110 citations*](https://md.research.elamur.ai/free/en/papers/liang-2023-gpt-detectors-biased-against-non/)
18. [**TextGrad: Automatic "Differentiation" via Text arXiv:2406.07496**Mert Yuksekgonul, Federico Bianchi, Joseph Boen, et al.*2024 · 96 citations*](https://md.research.elamur.ai/free/en/papers/yuksekgonul-2024-textgrad-automatic-differentiation-text/)
19. **[Mapping the Increasing Use of LLMs in Scientific Papers ↗](https://arxiv.org/abs/2404.01268) arXiv:2404.01268 · no summary yet**Weixin Liang et al.*2024 · 89 citations*
20. **[Spatial transcriptomic clocks reveal cell proximity effects in brain ageing ↗](https://doi.org/10.1038/s41586-024-08334-8) Nature · no summary yet**Eric Sun et al.*2024 · 89 citations*
21. **[In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering ↗](https://arxiv.org/abs/2311.06668) arXiv:2311.06668 · no summary yet**Sheng Liu et al.*2023 · 89 citations*
22. **[Concrete Autoencoders: Differentiable Feature Selection and Reconstruction. ↗](https://openalex.org/W2913375711) International Conference on Machine Learning · no summary yet**Muhammed Fati̇h Balin, Abubakar Abid, James Zou*2019 · 82 citations*
23. **[Quantifying large language model usage in scientific papers ↗](https://doi.org/10.1038/s41562-025-02273-8) Nature Human Behaviour · no summary yet**Weixin Liang et al.*2025 · 81 citations*
24. **[The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies ↗](https://doi.org/10.1101/2024.11.11.623004) bioRxiv 2024.11.11.623004; Nature (2025) · no summary yet**Kyle Swanson et al.*2024 · 76 citations*
25. **[ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://md.research.elamur.ai/free/en/papers/wu-2024-clasheval-quantifying-tug-war-between/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Kevin Wu, Eric Wu, James Zou*2024 · 65 citations*
26. [**Simple linear attention language models balance the recall-throughput tradeoff arXiv:2402.18668**Simran Arora, Sabri Eyuboglu, Michael Zhang, et al.*2024 · 59 citations*](https://md.research.elamur.ai/free/en/papers/arora-2024-simple-linear-attention-language-models/)
27. **[Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems ↗](https://arxiv.org/abs/2403.02419) arXiv (Cornell University) · no summary yet**Lingjiao Chen et al.*2024 · 46 citations*
28. **[Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models ↗](https://arxiv.org/abs/2510.04618) arXiv:2510.04618 · no summary yet**Qizheng Zhang et al.*2025 · 39 citations*
29. **[STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases ↗](https://doi.org/10.52202/079017-4037) neural information processing systems · no summary yet**Shirley Wu et al.*2024 · 38 citations*
30. **[Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory](https://md.research.elamur.ai/free/en/papers/suzgun-2026-dynamic-cheatsheet-test-time-learning/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Mirac Suzgun, Mert Yuksekgonul, Federico Bianchi, et al.*2026 · 37 citations*
31. **[AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning ↗](https://doi.org/10.52202/079017-0817) neural information processing systems · no summary yet**Shirley Wu et al.*2024 · 36 citations*
32. **[Factorized Contrastive Learning: Going Beyond Multi-view Redundancy ↗](https://doi.org/10.52202/075280-1430) neural information processing systems · no summary yet**Paul Pu Liang et al.*2023 · 32 citations*
33. **[CollabLLM: From Passive Responders to Active Collaborators ↗](https://arxiv.org/abs/2502.00640) arXiv (Cornell University) · no summary yet**Wu, Shirley et al.*2025 · 30 citations*
34. **[Language models cannot reliably distinguish belief from knowledge and fact ↗](https://doi.org/10.1038/s42256-025-01113-8) Nature Machine Intelligence · no summary yet**Mirac Süzgün et al.*2025 · 28 citations*
35. **[Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems ↗](https://doi.org/10.52202/079017-1455) neural information processing systems · no summary yet**Lingjiao Chen et al.*2024 · 27 citations*
36. **[How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis ↗](https://arxiv.org/abs/2402.05863) arXiv (Cornell University) · no summary yet**Federico Bianchi et al.*2024 · 22 citations*
37. **[Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025 ↗](https://arxiv.org/abs/2504.09737) arXiv:2504.09737 · no summary yet**Nitya Thakkar et al.*2025 · 21 citations*
38. **[TFG: Unified Training-Free Guidance for Diffusion Models ↗](https://doi.org/10.52202/079017-0704) neural information processing systems · no summary yet**Haotian Ye et al.*2024 · 16 citations*
39. **[Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models ↗](https://aclanthology.org/2023.findings-acl.472/) Findings of the Association for Computational Linguistics: ACL 2023 · no summary yet**Yuhui Zhang et al.*2023 · 16 citations*
40. **[Belief in the Machine: Investigating Epistemological Blind Spots of Language Models ↗](https://arxiv.org/abs/2410.21195) arXiv (Cornell University) · no summary yet**Mirac Süzgün et al.*2024 · 12 citations*
41. **[Diversifying history: A large-scale analysis of changes in researcher demographics and scholarly agendas ↗](https://doi.org/10.1371/journal.pone.0262027) PLoS ONE · no summary yet**Stephan Risi et al.*2022 · 11 citations*
42. **[Science Across Languages: Assessing LLM Multilingual Translation of Scientific Papers ↗](https://aclanthology.org/2026.findings-eacl.204/) Findings of the Association for Computational Linguistics: EACL 2026 · no summary yet**Hannah Calzi Kleidermacher, James Zou*2026 · 10 citations*
43. **[Optimizing Model Selection for Compound AI Systems ↗](https://arxiv.org/abs/2502.14815) arXiv (Cornell University) · no summary yet**Lingjiao Chen et al.*2025 · 9 citations*
44. **[GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts ↗](https://doi.org/10.52202/079017-0297) neural information processing systems · no summary yet**Shirley Wu et al.*2024 · 9 citations*
45. **[UQ: Assessing Language Models on Unsolved Questions ↗](https://arxiv.org/abs/2508.17580) arXiv (Cornell University) · no summary yet**Nie, Fan et al.*2025 · 6 citations*
46. **[OctoTools: A Multi-Agent Framework with Extensible Tools for Complex Reasoning](https://md.research.elamur.ai/free/en/papers/lu-2026-octotools-multi-agent-framework-extensible/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Pan Lu, Bowen Chen, Sheng Liu, et al.*2026 · 5 citations*
47. **[HumanLM: Simulating Users with State Alignment Beats Response Imitation ↗](https://arxiv.org/abs/2603.03303) arXiv (Cornell University) · no summary yet**Wu, Shirley et al.*2026 · 5 citations*
48. **[Redefining druggable targets with artificial intelligence ↗](https://doi.org/10.1038/s41587-025-02770-1) Nature Biotechnology · no summary yet**Karen Akinsanya et al.*2025 · 4 citations*
49. **[Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards ↗](https://arxiv.org/abs/2507.03041) arXiv (Cornell University) · no summary yet**Wu, Shirley et al.*2025 · 4 citations*
50. **[Data-regularized Reinforcement Learning for Diffusion Models at Scale ↗](https://arxiv.org/abs/2512.04332) arXiv:2512.04332 · no summary yet**Haotian Ye et al.*2025 · 4 citations*
51. **[Combee: Scaling Prompt Learning for Self-Improving Language Model Agents ↗](https://arxiv.org/abs/2604.04247) arXiv (Cornell University) · no summary yet**Hanchen Li et al.*2026 · 3 citations*
52. **[Exploring the use of AI authors and reviewers at Agents4Science ↗](https://arxiv.org/abs/2511.15534) arXiv:2511.15534 · no summary yet**Federico Bianchi et al.*2025 · 2 citations*
53. **[CHORDS: Diffusion Sampling Accelerator with Multi-Core Hierarchical ODE Solvers ↗](https://doi.org/10.1109/iccv51701.2025.01802) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Jiaqi Han et al.*2025 · 2 citations*
54. **[Reasoning or Knowledge: Stratified Evaluation of Biomedical LLMs](https://md.research.elamur.ai/free/en/papers/thapa-2026-reasoning-or-knowledge-stratified-evaluation/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Rahul Thapa, Qingyang Wu, Kevin Wu, et al.*2026 · 1 citation*
55. **[The Price Reversal Phenomenon: When Cheaper Reasoning Models Cost More ↗](https://arxiv.org/abs/2603.23971) arXiv (Cornell University) · no summary yet**Lingjiao Chen et al.*2026 · 1 citation*
56. **[CollabLLM: From Passive Responders to Active Collaborators (Extended Abstract) ↗](https://doi.org/10.24963/ijcai.2026/928) International Joint Conference on Artificial Intelligence · no summary yet**Shirley Wu et al.*2026 · 1 citation*
57. **[How random is the review outcome? A systematic study of the impact of external factors on eLife peer review ↗](https://doi.org/10.1101/2023.01.04.522708) bioRxiv (Cold Spring Harbor Laboratory) · no summary yet**Weixin Liang et al.*2023 · 1 citation*
58. **[Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment ↗](https://arxiv.org/abs/2603.21597) arXiv (Cornell University) · no summary yet**Sheng Liu et al.*2026*
59. **[Evaluating Commercial AI Chatbots as News Intermediaries ↗](https://arxiv.org/abs/2605.22785) arXiv (Cornell University) · no summary yet**Mirac Süzgün et al.*2026*
60. **[string2string Studio: An Interactive, In-Browser Platform for String-to-String Algorithms ↗](https://arxiv.org/abs/2608.03984) arXiv (Cornell University) · no summary yet**Mirac Süzgün et al.*2026*
61. **[Generative AI for drug design : methods and applications ↗](https://doi.org/10.25740/kn208rt3658) Stanford Digital Repository · no summary yet**Kyle Swanson et al.*2026*
62. **[Collaborative AI agents ↗](https://doi.org/10.25740/kt076zd0858) Stanford Digital Repository · no summary yet**Shirley Yingxin Wu et al.*2026*
63. **[REAR: Rethinking Visual Autoregressive Models via Generator-Tokenizer Consistency Regularization ↗](https://arxiv.org/abs/2510.04450) arXiv (Cornell University) · no summary yet**He, Qiyuan et al.*2025*
64. **[InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression ↗](https://arxiv.org/abs/2512.16975) arXiv (Cornell University) · no summary yet**Haotian Ye et al.*2025*
65. **[GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters ↗](https://arxiv.org/abs/2507.02085) arXiv (Cornell University) · no summary yet**Wanjia Zhao et al.*2025*
66. **[Diversifying History ↗](https://doi.org/10.17605/osf.io/v4ysh) no summary yet**Stephan Risi et al.*2021*