We introduce the GEM (Generative Estimator for Mutual Information), an evaluation metric for assessing language generation by large language models (LLMs), particularly in generating informative judgments, without the need for a gold standard reference. GEM broadens the scenarios where we can benchmark LLM generation performance-from traditional ones, like machine translation and summarization, where gold standard references are readily available, to subjective tasks without clear gold standards, such as academic peer review. GEM uses a generative model to estimate mutual information between candidate and reference responses, without requiring the reference to be a gold standard. In experiments on two human-annotated datasets, GEM demonstrates competitive correlations with human scores compared to the state-of-the-art GPT-4o Examiner, and outperforms all other baselines. Additionally, GEM is more robust against strategic manipulation, such as rephrasing or elongation, which can artificially inflate scores under a GPT-4o Examiner. We also present GRE-bench (Generating Review Evaluation Benchmark) which evaluates LLMs based on how well they can generate high-quality peer reviews for academic research papers. Because GRE-bench is based upon GEM, it inherits its robustness properties. Additionally, GRE-bench circumvents data contamination problems (or data leakage) by using the continuous influx of new open-access research papers and peer reviews each year. We show GRE-bench results of various popular LLMs on their peer review capabilities using the ICLR2023 dataset.

Peer prediction mechanisms motivate high-quality feedback with provable guarantees. However, current methods only apply to rather simple reports, like multiple-choice or scalar numbers. We aim to broaden these techniques to the larger domain of text-based reports, drawing on the recent developments in large language models (LLMs). This vastly increases the applicability of peer prediction mechanisms as textual feedback is the norm in a large variety of feedback channels: peer reviews, e-commerce customer reviews, and comments on social media.

Peer review lies at the core of the academic process, but even well-intentioned reviewers can still provide noisy ratings. While ranking papers by average ratings may reduce noise, varying noise levels and systematic biases stemming from ``cheap'' signals (e.g. author identity, proof length) can lead to unfairness. Detecting and correcting bias is challenging, as ratings are subjective and unverifiable. Unlike previous works relying on prior knowledge or historical data, we propose a one-shot noise calibration process without any prior information. We ask reviewers to predict others' scores and use these predictions for calibration. Assuming reviewers adjust their predictions according to the noise, we demonstrate that the calibrated score results in a more robust ranking compared to average ratings, even with varying noise levels and biases. In detail, we show that the error probability of the calibrated score approaches zero as the number of reviewers increases and is significantly lower compared to average ratings when the number of reviewers is small.

A transaction fee mechanism (TFM) is an essential component of a blockchain protocol. However, a systematic evaluation of the real-world impact of TFMs is still absent. Using rich data from the Ethereum blockchain, the mempool, and exchanges, we study the effect of EIP-1559, one of the earliest-deployed TFMs that depart from the traditional first-price auction paradigm. We conduct a rigorous and comprehensive empirical study to examine its causal effect on blockchain transaction fee dynamics, transaction waiting times, and consensus security. Our results show that EIP-1559 improves the user experience by mitigating intrablock differences in the gas price paid and reducing users' waiting times. However, EIP-1559 has only a small effect on gas fee levels and consensus security. In addition, we find that when Ether's price is more volatile, the waiting time is significantly higher. We also verify that a larger block size increases the presence of siblings. These findings suggest new directions for improving TFMs.

With the development of blockchain applications, the requirements for file storage in blockchain are increasing rapidly. Many protocols, including Filecoin, Arweave, and Sia, have been proposed to provide scalable decentralized file storage for blockchain applications. However, the reliability is not well promised by existing protocols. Inspired by the idea of insurance, we innovatively propose a decentralized file storage protocol in blockchain, named as FileInsurer, to achieve both scalability and reliability. While ensuring scalability by distributed storage, FileInsurer guarantees reliability by enhancing robustness and fully compensating for the file loss. Specifically, under mild conditions, we prove that no more than 0.1% value of all files should be compensated even if half of the storage collapses. Therefore, only a relatively small deposit needs to be pledged by storage providers to cover the potential file loss. Because of lower burdens of deposit, storage providers have more incentives to participate in the storage network. FileInsurer can run in the top layer of the InterPlanetary File System (IPFS), and thus it can be directly applied in Web 3.0, Non-Fungible Tokens, and Metaverse.

Information flow measures, over the duration of a game, the audience’s belief of who will win, and thus can reflect the amount of surprise in a game. To quantify the relationship between information flow and audiences' perceived quality, we conduct a case study where subjects watch one of the world’s biggest esports events, LOL S10. In addition to eliciting information flow, we also ask subjects to report their rating for each game. We find that the amount of surprise in the end of the game plays a dominant role in predicting the rating. This suggests the importance of incorporating when the surprise occurs, in addition to the amount of surprise, in perceived quality models. For content providers, it implies that everything else being equal, it is better for twists to be more likely to happen toward the end of a show rather than uniformly throughout.