% Key papers for Statistical frameworks for LLM evaluation (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2020_the_29881,
  title = {{The Curious Case of Neural Text Degeneration}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rygGQyrFvH},
}

@inproceedings{icml2024_improving_45832,
  title = {{Improving Factuality and Reasoning in Language Models through Multiagent Debate}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32620},
}

@inproceedings{neurips2023_large_66900,
  title = {{Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73693},
}

@inproceedings{neurips2022_factuality_64687,
  title = {{Factuality Enhanced Language Models for Open-Ended Text Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54386},
}

@inproceedings{iclr2023_semantic_32682,
  title = {{Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11013},
}

@inproceedings{neurips2022_capturing_65614,
  title = {{Capturing Failures of Large Language Models via Human Cognitive Biases}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53539},
}

@inproceedings{iclr2023_roscoe_33384,
  title = {{ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11337},
}

@inproceedings{iclr2024_lmsys_33856,
  title = {{LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19219},
}

@inproceedings{iclr2024_large_35435,
  title = {{Large Language Models Are Not Robust Multiple Choice Selectors}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17638},
}

@inproceedings{neurips2021_is_63370,
  title = {{Is Automated Topic Model Evaluation Broken? The Incoherence of Coherence}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27300},
}

@inproceedings{iclr2024_prometheus_33754,
  title = {{Prometheus: Inducing Fine-Grained Evaluation Capability in Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19321},
}

@inproceedings{aaai2021_perception_1160,
  title = {{Perception Score: A Learned Metric for Open-ended Text Generation Evaluation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/12902-perception-score-a-learned-metric-for-open-ended-text-generation-evaluation/},
}

@inproceedings{iclr2024_conformal_35318,
  title = {{Conformal Language Modeling}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17755},
}

@inproceedings{icml2024_mllm_44907,
  title = {{MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33545},
}

@inproceedings{aaai2025_self_10603,
  title = {{SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34603},
}

@inproceedings{neurips2024_large_71535,
  title = {{Large language model validity via enhanced conformal prediction methods}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95729},
}

@inproceedings{icml2024_distinguishing_45633,
  title = {{Distinguishing the Knowable from the Unknowable with Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32819},
}

@inproceedings{icml2025_correlated_48391,
  title = {{Correlated Errors in Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44225},
}

@inproceedings{neurips2023_face_69744,
  title = {{FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70195},
}

@inproceedings{icml2024_characterizing_43562,
  title = {{Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34890},
}

@inproceedings{icml2024_is_44793,
  title = {{Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33659},
}

@inproceedings{icml2025_facter_48031,
  title = {{FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44576},
}

@inproceedings{icml2026_verbalized_55507,
  title = {{Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=zloIrd77G5},
}

@inproceedings{neurips2024_mixeval_70572,
  title = {{MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96545},
}

@inproceedings{neurips2024_clave_71647,
  title = {{CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97747},
}

@inproceedings{aaai2025_dsgram_8625,
  title = {{DSGram: Dynamic Weighting Sub-Metrics for Grammatical Error Correction in the Era of Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34746},
}

@inproceedings{aaai2025_understanding_11143,
  title = {{Understanding Annotator Perception: Modeling Psychological Inference from First- and Third-Person Annotations (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35321},
}

@inproceedings{iclr2024_closing_34814,
  title = {{Closing the Curious Case of Neural Text Degeneration}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18260},
}

@inproceedings{icml2025_improving_46141,
  title = {{Improving Your Model Ranking on Chatbot Arena by Vote Rigging}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46419},
}