Machine learning predictions are increasingly used to supplement incomplete or costly-to-measure outcomes in fields such as biomedical research, environmental science, and social science. However, treating predictions as ground truth introduces bias while ignoring them wastes valuable information. Prediction-Powered Inference (PPI) offers a principled framework that leverages predictions from large unlabeled datasets to improve statistical efficiency while maintaining valid inference through explicit bias correction using a smaller labeled subset. Despite its potential, the growing PPI variants and the subtle distinctions between them have made it challenging for practitioners to determine when and how to apply these methods responsibly. This paper demystifies PPI by synthesizing its theoretical foundations, methodological extensions, connections to existing statistics literature, and diagnostic tools into a unified practical workflow. Using the Mosaiks housing price data, we show that PPI variants produce tighter confidence intervals than complete-case analysis, but that double-dipping, i.e. reusing training data for inference, leads to anti-conservative confidence intervals and coverages. Under missing-not-at-random mechanisms, all methods, including classical inference using only labeled data, yield biased estimates. We provide a decision flowchart linking assumption violations to appropriate PPI variants, a summary table of selective methods, and practical diagnostic strategies for evaluating core assumptions. By framing PPI as a general recipe rather than a single estimator, this work bridges methodological innovation and applied practice, helping researchers responsibly integrate predictions into valid inference.

With a rapid growth in the deployment of AI tools for making critical decisions (or aiding humans in doing so), there is a growing demand to be able to explain to the stakeholders how these tools arrive at a decision. Consequently, voting is frequently used to make such decisions due to its inherent explainability. Recent work suggests that using randomized (as opposed to deterministic) voting rules can lead to significant efficiency gains measured via the distortion framework. However, rules that use intricate randomization can often become too complex to explain to the stakeholders; losing explainability can eliminate the key advantage of voting over black-box AI tools, which may outweigh the efficiency gains.We study the efficiency gains which can be unlocked by using voting rules that add a simple randomization step to a deterministic rule, thereby retaining explainability. We focus on two such families of rules, randomized positional scoring rules and random committee member rules, and show, theoretically and empirically, that they indeed achieve explainability and efficiency simultaneously to some extent.

Algorithms have been estimated to increase AI training FLOP efficiency by a factor of 22,000 between 2012 and 2023 [Ho et al., 2024]. Running small-scale ablation experiments on key innovations from this time period, we are able to account for less than 10x of these gains. Surveying the broader literature, we estimate that additional innovations not included in our ablations account for less than 10x, yielding a total under 100x. This leads us to conduct scaling experiments, which reveal that much of this efficiency gap can be explained by algorithms with scale-dependent efficiency improvements. In particular, we conduct scaling experiments between LSTMs and Transformers, finding exponent differences in their compute-optimal scaling law while finding little scaling difference for many other innovations. These experiments demonstrate that - contrary to standard assumptions - an algorithm's efficiency gains are tied to compute scale. Using experimental extrapolation and literature estimates, we account for 6,930x efficiency gains over the same time period, with the scale-dependent LSTM-to-Transformer transition accounting for the majority of gains. Our results indicate that algorithmic progress for small models has been far slower than previously assumed, and that measures of algorithmic efficiency are strongly reference-dependent.

We provide additional experimental results to supplement Section 6 . In Section B.1, we include In Section B.2, we present a few example outputs with a visualization In Section B.3, we include results Figure B.1 and Figure B.2 present the empirical The bottom row presents the average number of decoder layer used. The bottom row presents the average number of decoder layer used. Figure B.5 presents two example outputs of CALM for instances from the machine translation, and We observe that the textual distance generally increases as we accelerate the decoding. Interestingly, following our initial intuition, CALM distributes the compute unevenly, using very few layers for certain "easy" tokens, and additional compute to "hard" tokens.

This position paper challenges the "scaling fundamentalism" dominating AI research, where unbounded growth in model size and computation has led to unsustainable environmental impacts and widening resource inequality. We argue that LLM development should be fundamentally reoriented toward capability-per-resource rather than capability alone. We present a theoretical framework demonstrating that resource-allocation decisions guided by gradient influence patterns can dramatically improve efficiency throughout the AI lifecycle. Our analysis shows that in transformer-based models, where a small fraction of parameters exert outsized influence (following heavy-tailed distributions), three critical insights emerge: (1) updating only high-influence parameters strictly outperforms full-parameter tuning on a performance-per-resource basis; (2) simple gradient norms provide computationally efficient proxies for identifying these high-influence components; and (3) coordinated parameter and data selection yields multiplicative efficiency gains, potentially reducing resource requirements by orders of magnitude. Building on these theoretical foundations, we propose a two stage paradigm marginal-return pretraining for foundation developers and influence guided adaptation for downstream users bridged by gradient blueprints, metadata describing which parameters matter most for various tasks. This capability-per-resource perspective transforms what were once considered pragmatic hardware workarounds into theoretically optimal strategies, democratizing access to cutting-edge AI capabilities while significantly reducing environmental impact. By embedding resource consciousness into how we develop, adapt, and evaluate models, we can reshape AI progress toward a more sustainable and equitable future.

It is often claimed that machine learning-based generative AI products will drastically streamline and reduce the cost of legal practice. This enthusiasm assumes lawyers can effectively manage AI's risks. Cases in Australia and elsewhere in which lawyers have been reprimanded for submitting inaccurate AI-generated content to courts suggest this paradigm must be revisited. This paper argues that a new paradigm is needed to evaluate AI use in practice, given (a) AI's disconnection from reality and its lack of transparency, and (b) lawyers' paramount duties like honesty, integrity, and not to mislead the court. It presents an alternative model of AI use in practice that more holistically reflects these features (the verification-value paradox). That paradox suggests increases in efficiency from AI use in legal practice will be met by a correspondingly greater imperative to manually verify any outputs of that use, rendering the net value of AI use often negligible to lawyers. The paper then sets out the paradox's implications for legal practice and legal education, including for AI use but also the values that the paradox suggests should undergird legal practice: fidelity to the truth and civic responsibility.