Unified framework for certifying LLM reliability without extra supervision.
problem Improving reliability of large language models without additional supervision.
method Unified framework using majority voting and Martingale Majority Certificate (MMC).
result Certifiable inference in LLMs with statistical guarantees and adaptive stopping rules.
LLMs' explanations are often insufficient and vary with input distribution.
problem Evaluating the sufficiency of LLM explanations without predefined biases.
method Generalizing sufficiency to arbitrary explanations, using LLM's input beliefs, and introducing SCSuff metric.
result Explanation sufficiency can vary with input distribution and is weakly correlated with model size, accuracy, or output entropy.
CITE algorithm provides anytime-valid certification of model outputs.
problem Challenges in controlling error levels in LLM self-consistency.
method Certification by Intersection-union Testing with E-processes (CITE) algorithm.
result Provable control of false certification at any prescribed level under arbitrary stopping rules.
Blend-ASC improves self-consistency efficiency by dynamically allocating samples, reducing costs.
problem Efficiently applying self-consistency to large datasets is computationally expensive.
method Blend-ASC dynamically allocates samples during inference, improving efficiency.
result Blend-ASC reduces sample usage by 6.8x on average compared to vanilla self-consistency.
Improved selection of best outputs from LLMs for better accuracy.
problem BoN fails to reliably find the correct answer with imperfect rewards.
method Majority-of-the-Bests (MoB) selects the mode of a bootstrapped output distribution of BoN.
result MoB consistently improves over BoN in 25 out of 30 setups.
This work explores test-time scaling strategies for LLMs, improving sample efficiency and expressiveness.
problem Understanding the sample efficiency and expressiveness of test-time scaling strategies for LLMs.
method Established separation and expressiveness results for self-consistency, best-of-n, and self-correction strategies. result Self-correction enables Transformers to simulate online learning over multiple tasks without prior knowledge.
FSPO optimizes synthetic preferences for LLM personalization.
problem Personalizing large language models for diverse users.
method FSPO reframes reward modeling as a meta-learning problem, using few labeled preferences and synthetic data.
result FSPO achieves high winrates in personalized responses, both synthetic and real.
Formalizes weak and strong verification for LLMs, controlling errors without assumptions.
problem Balancing cost and reliability in reasoning with LLMs.
method Formalizes weak-strong verification policies, introduces metrics, develops online algorithm.
result Optimal policies admit a two-threshold structure, and calibration and sharpness govern value of weak verifiers.
A new framework evaluates LLM calibration in open-ended QA.
problem Evaluating LLM calibration in open-ended QA settings.
method Sem-ECE framework: sampling answers, grouping by semantic classes, and using frequencies as confidence.
result Sem-ECE estimators are unbiased and Sem2 achieves smaller calibration error. Sequence probability predicts correctness in LLMs, but not for repeated prompts
problem Predicting correctness in large language models
method Quantifying sequence probability and correctness across different levels
result Higher sequence probability often predicts correctness across prompt-answer pairs
Self-consistent models improve reinforcement learning by aligning predictions with future values.
problem Improving reinforcement learning by aligning model predictions with future values.
method Proposes multiple self-consistency updates to encourage a learned model and value function to be consistent with each other.
result Self-consistency helps both policy evaluation and control in both tabular and function approximation settings.
Analyzes feature learning in neural networks using a self-consistent dynamical field theory.
problem Feature learning in infinite-width neural networks.
method Constructs deterministic dynamical order parameters as inner-product kernels for hidden unit activations and gradients.
result Reveals the hidden layer activation distribution, neural tangent kernel evolution, and output predictions.
We discuss the foundations of factor or regression models in the light of the self-consistency condition that the market portfolio (and more generally the risk factors) is (are) constituted of the assets whose returns it is (they are) supposed to explain. As already reported in several articles, self-consistency implie…
Motion of curves and surfaces in R3 lead to nonlinear evolution equations which are often integrable. They are also intimately connected to the dynamics of spin chains in the continuum limit and integrable soliton systems through geometric and gauge symmetric connections/equivalence. Here we point out the fact that…
This work analyzes CoT prompting methods from a statistical estimation perspective.
problem Improving the effectiveness of LLMs in solving multi-step reasoning problems.
method Introducing a multi-step latent variable model to characterize CoT prompting from a statistical estimation viewpoint.
result The CoT estimator is equivalent to a Bayesian estimator when the pretraining dataset is large.
ORCA calibrates LLMs for efficient, generalizable reasoning.
problem Miscalibration of large language models leading to inefficiencies.
method Online Reasoning Calibration (ORCA) using conformal prediction and test-time training.
result ORCA provides higher efficiency and generalization across different reasoning tasks.
The paper certifies AI reliability via sampling and calibration, providing exact guarantees.
problem Ensuring trust in black-box AI systems' outputs.
method Self-consistency sampling and conformal calibration.
result Reliability levels derived from these methods offer finite-sample guarantees.
Self-consistency improves the accuracy of model comparison methods.
problem Improving the accuracy of model comparison methods when simulation models are misspecified.
method Supplement traditional simulation-based training with a self-consistency loss on unlabeled real data.
result Self-consistency training improves model comparison accuracy, especially in open-world scenarios.
VAEs improve representation learning by inverting the data-generating process through self-consistency.
problem VAEs struggle to invert the data-generating process, yet often succeed in representation learning.
method Studied VAEs in the limit of near-deterministic decoders, proving self-consistency and showing ELBO convergence to a regularized log-likelihood.
result VAEs can perform independent mechanism analysis (IMA), recovering true latent factors under specific conditions.
From SA-CCR to RSA-CCR: making SA-CCR self-consistent and appropriately risk-sensitive by cashflow decomposition in a 3-Factor Gaussian Market Model
Theory captures feature learning effects in finite CNNs.
problem Feature learning in finite deep neural networks.
method Derive a self-consistent Gaussian Process theory.
result Good agreement with experiments and sharp transition between regimes.
New algorithm calibrates local volatility from option prices using deep neural networks.
problem Calibrating local volatility from market option prices with reduced interpolation and reprice errors.
method Deep self-consistent learning using neural networks to approximate both option prices and local volatility.
result Improved performance in terms of reduced interpolation and reprice errors compared to existing methods.
VAE fails to encode typical samples, new method improves robustness.
problem VAE does not necessarily encode typical samples generated by its decoder.
method Alternative construction of variational approximation distribution, self-consistency approach.
result Encoders trained with self-consistency approach are robust to adversarial attacks.
Paper improves robustness of ABI with unlabeled data.
problem Robustness issues in ABI for out-of-simulation data.
method Semi-supervised approach using unlabeled data and self-consistency losses.
result Semi-supervised ABI with unlabeled data improves robustness significantly.
New method learns diffusion bridges for rare events.
problem Simulating rare events in diffusion processes.
method Iterative online learning based on self-consistency.
result Strong performance in various empirical settings.
New metric reduces arbitrariness in fair binary classification predictions.
problem Variance in predictions leads to arbitrary decisions in fair classification.
method Developed a self-consistency metric and an abstention algorithm.
result Fair binary classification is often close to fair due to variance, not interventions.
New method uses neural networks for estimating survival functions from censored data.
problem Estimating conditional survival functions from censored time-to-event data with complex predictors.
method Generative adversarial networks leveraging self-consistent equations, without parametric assumptions.
result Established the convergence rate of the proposed estimator.
SC improves robustness in model comparison for misspecified models.
problem Model misspecification challenges in amortized Bayesian inference.
method Parameter posterior-based methods augmented with SC training.
result SC improves robustness under model misspecification.
New method generates clean data from corrupted observations.
problem Generating clean data from corrupted observations.
method Iterative update of a transport map using black-box corruption channel access.
result Converges to a self-consistent transport map that effectively inverts the corruption channel.
SNAP improves robust computation by emphasizing trustworthy items and downweighting outliers.
problem Improving robustness in computation, especially in high-dimensional settings.
method SNAP assigns weights based on mutual agreement, suppressing outlier contributions.
result SNAP ensures outliers contribute negligibly to computations, even in high-dimensional settings.
The Mondrian process represents an elegant and powerful approach for space partition modelling. However, as it restricts the partitions to be axis-aligned, its modelling flexibility is limited. In this work, we propose a self-consistent Binary Space Partitioning (BSP)-Tree process to generalize the Mondrian process. Th…
Traditional methods outperform LLMs in forecasting corporate credit ratings.
problem Forecasting corporate credit ratings using LLMs.
method Comparison of traditional methods (XGBoost) and LLMs (LLaMA) on credit rating forecasting.
result XGBoost outperforms LLMs in forecasting corporate credit ratings.
Unified framework to bridge human and LLM judgments.
problem Systematic discrepancies between human and LLM evaluations.
method Latent human preference score and linear transformations of covariates.
result Higher agreement with human ratings and exposure of systematic gaps.
LLM-Lasso uses LLMs to improve feature selection in Lasso regression.
problem Improving feature selection in Lasso regression with domain-specific knowledge.
method Combines LLMs with Lasso regularization to generate feature weights.
result Outperforms standard Lasso and feature selection baselines in biomedical studies.
THERMOMETER calibrates LLMs efficiently for diverse tasks.
problem Calibrating large language models is challenging due to computational and versatility issues.
method THERMOMETER learns an auxiliary model for calibrating a LLM using data from multiple tasks.
result THERMOMETER produces better-calibrated responses for new tasks.
Regurgitative training with synthetic data harms LLM performance.
problem The impact of training LLMs with synthetic data generated by other LLMs.
method Fine-tuning GPT-3.5 with synthetic and real data in a machine translation task.
result Regurgitative training significantly reduces LLM performance.
FLUID-LLM uses LLMs to predict fluid dynamics with improved accuracy.
problem Leveraging LLMs for CFD due to their pattern recognition abilities but struggles with fluid dynamics complexities.
method Combines pre-trained LLMs with spatiotemporal-aware encoding to predict unsteady fluid dynamics.
result Significant performance improvements in CFD predictions across various datasets.
This paper improves continuous adversarial training for LLMs using in-context learning theory.
problem Efficiently defending large language models (LLMs) against jailbreak attacks.
method The paper presents a theoretical analysis of continuous adversarial training (CAT) for LLMs based on in-context learning (ICL) theory, proving a robust generalization bound and proposing an improved regularization term.
result The robust generalization bound explains why CAT can defend against jailbreak prompts and shows that LLM robustness is related to embedding matrix singular values.
LLMs mimic human traders in finance, but not as much as expected.
problem Evaluating how LLMs behave in financial markets.
method Adapted experimental design with LLMs and human traders, analyzed in single and mixed model settings.
result LLMs tend to price assets near their fundamental value, but not as much as humans, and show less trading strategy variance.
Paper presents a probabilistic model to improve LLM cascade performance.
problem Complexity of LLM cascades and their interaction error rates.
method Probabilistic model for joint performance distribution of LLMs.
result Improves area under the error-cost curve by 4.3% on average for cascades with k≥3 models.
LLMs struggle to optimize hyperparameters efficiently, but hybrid methods can improve performance.
problem Optimizing hyperparameters of small language models using LLMs.
method Comparison of classical HPO algorithms and LLM-based methods, introducing Centaur hybrid approach.
result Hybrid Centaur approach achieves best results, outperforming classical and pure LLM methods.
Improves feature selection in high-dimensional data using LLM-generated weights.
problem Inaccurate LLM-generated weights degrade feature selection performance.
method Integrates LLM-generated weights into prior inclusion probabilities using LLM Sparsity Prior (LSP).
result Improves prediction accuracy and identifies clinically relevant features.
Telescope detects LLM generated text by measuring token repetition probability.
problem Distinguishing LLM generated text from human writing.
method Telescope Perplexity, evaluating token repetition probability.
result Telescope Perplexity enables effective zero-shot LLM detection.
BED-LLM uses Bayesian experimental design to improve LLMs' information gathering.
problem Improving LLMs' ability to gather information adaptively.
method Iteratively choosing questions to maximize expected information gain using a probabilistic model.
result BED-LLM achieves substantial performance gains compared to other adaptive design strategies.
New benchmarks show LLMs struggle with causal discovery.
problem Leveraging LLMs for causal discovery is unreliable due to dataset leakage.
method Developing science-grounded benchmarks and hybrid methods combining LLM predictions with statistical analysis.
result LLMs perform poorly on novel, real-world scientific studies compared to classical methods.
Machine learning is used to approximate the kinetic energy of one dimensional diatomics as a functional of the electron density. The functional can accurately dissociate a diatomic, and can be systematically improved with training. Highly accurate self-consistent densities and molecular forces are found, indicating the…
Tiny benchmarks reduce LLM evaluation costs by using fewer examples.
problem Expensive evaluation of LLMs with tens of thousands of examples.
method Developed evaluation tools and tiny versions of popular benchmarks.
result Accurately estimate LLM performance with just 100 curated examples.
SelfReflect measures LLM uncertainty by summarizing belief distribution.
problem LLMs lack transparency in expressing uncertainty.
method Developed SelfReflect metric to quantify uncertainty.
result Modern LLMs cannot reflect their uncertainty.