Study shows multilingual LLM calibration effects improve model confidence but not accuracy.
problem Improving multilingual language model calibration in low-resource settings.
method Analysis of two multilingual benchmarks using instruction-tuning and label smoothing.
result Model confidence increases in low-resource languages after instruction-tuning but accuracy improvements are marginal.
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.
Building accurate language models that capture meaningful long-term dependencies is a core challenge in natural language processing. Towards this end, we present a calibration-based approach to measure long-term discrepancies between a generative sequence model and the true distribution, and use these discrepancies to …
The paper addresses poor calibration in fine-tuned LLMs after preference alignment.
problem Poor calibration in fine-tuned Large Language Models (LLMs) after preference alignment.
method Proposes a calibration-aware fine-tuning approach to restore calibration without compromising model performance.
result Demonstrates the effectiveness of the proposed methods through extensive experiments.
This paper investigates uncertainty calibration in multimodal large language models.
problem Challenges in properly calibrating uncertainty in multimodal large language models.
method Investigation of representative MLLMs across various scenarios, including visual fine-tuning and multimodal training.
result MLLMs tend to give answers rather than admit uncertainty, but this self-assessment improves with proper prompt adjustments.
Improved IVON boosts LoRA model accuracy and calibration.
problem Improving the accuracy and calibration of large language models.
method Replaced AdamW with IVON for finetuning Llama-2.
result IVON improves Llama-2 accuracy by 2.8% and calibration error by 4.6%.
New framework assesses LM uncertainty without thresholding.
problem Uncertainty quantification for LMs, especially comparing different measures.
method Rank-Calibration framework to assess uncertainty and confidence measures.
result Higher uncertainty correlates with lower generation quality.
This work tackles uncertainty quantification in language models, proposing a principled approach.
problem Challenges in identifying task-specific uncertainties in large language models.
method Bayesian decision theory, focusing on a similarity measure between generated and hypothetical true responses.
result Derives a measure for epistemic uncertainty based on a missing data perspective.
Generative models often misrepresent class frequencies; this paper calibrates them.
problem Miscalibration of class frequencies in generative models.
method Formulated as constrained optimization, using surrogate objectives to approximate constraints.
result Significant reduction in calibration error across various models and applications.
The semantic map calibrates uncertainty from language model probabilities.
problem Uncertainty in language model probabilities for professional decisions.
method Prespecified semantic map linking probabilities of verbal responses to probabilities of declared states.
result Language-derived probabilities outperform printed numerical probabilities and recover valid uncertainty coverage.
The study examines label smoothing to improve confidence calibration in fine-tuned LLMs.
problem Improving confidence calibration in fine-tuned large language models (LLMs) after instruction tuning.
method Examine various open-sourced LLMs, label smoothing, and custom kernel design.
result Label smoothing is effective in maintaining confidence calibration but faces challenges in large vocabulary LLMs.
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.
Study recommends PLM choices for minimizing calibration error in NLP tasks.
problem Minimizing calibration error in PLM-based NLP predictions.
method Compared various options for PLM encoding, size, uncertainty quantifier, and fine-tuning loss.
result Recommendations for a well-calibrated PLM-based prediction pipeline.
LLMs show surprising confidence in their answers, beyond just tokens.
problem LLMs lack meaningful confidence estimates for their responses.
method Semantic calibration test based on local loss optimality and equivalence classes.
result Base LLMs are semantically calibrated across tasks, contrary to expectations.
The paper studies entropy calibration in language models and finds that miscalibration improves slowly with scale.
problem The problem is whether language model entropy calibration improves with scale and if it's possible to calibrate without reducing log loss.
method The authors study a simplified theoretical setting to characterize miscalibration scaling behavior and measure it empirically in language models ranging from 0.5B to 70B parameters.
result The observed scaling behavior of miscalibration is similar to theoretical predictions, indicating slow improvement with scale. The authors also prove theoretically that it is possible to reduce entropy while preserving log loss if access to a black box predicting future entropy is available.
Linguistic calibration improves long-form text confidence.
problem LMs hallucinate, leading to suboptimal decisions.
method Defining linguistic calibration, training framework, reinforcement learning.
result Llama 2 7B is significantly more calibrated than baselines.
ABC improves uncertainty quantification in LLMs for clinical diagnostics.
problem Overconfident and poorly calibrated estimates of LLMs in clinical domains.
method Approximate Bayesian Computation (ABC) for likelihood-free inference.
result Improves accuracy by up to 46.9%, reduces Brier scores by 74.4%, and enhances calibration.
Calibrated PRMs improve inference efficiency for LLMs by dynamically adjusting compute budgets.
problem Poor calibration of PRMs leads to overestimation of success probabilities in partial reasoning steps.
method Quantile regression for calibration, instance-adaptive scaling (IAS) framework.
result Calibrated PRMs reduce inference costs while maintaining accuracy, especially on confident problems.
The study examines how much data is needed for generative and vision-language models to make reliable predictions.
problem Ensuring reliable predictions with low data for models used in medical decision support.
method Analyzes uniform convergence bounds for VLM-induced classifiers under low-dimensional semantic representations.
result Finite-sample uniform convergence bounds for accuracy and calibration functionals of VLM-induced classifiers.
G-Sim uses LLMs to build reliable simulators for complex systems.
problem Building robust simulators for critical domains like healthcare and logistics is challenging.
method Hybrid framework combining LLM-driven structural design and empirical calibration.
result G-Sim produces reliable, causally-informed simulators that handle non-differentiable and stochastic simulators.
New method samples from LLM posterior for coherent, useful responses.
problem Hallucinations in large language models.
method Posterior sampling for conditional generation, with calibration.
result Achieves statistical guarantees with higher downstream utility.
This work shows fine-tuning improves LLM uncertainty estimates efficiently.
problem Ensuring high-stakes predictions from large language models.
method Fine-tuning on a small dataset of correct and incorrect answers.
result Fine-tuned LLMs produce good generalization and tractable uncertainty estimates.
Cost-effective method detects language model hallucinations.
problem Detecting unreliable outputs from LLMs.
method Pipeline including confidence score, input attributes calibration, and thresholding.
result Multi-scoring framework outperforms individual methods and reduces computational cost.
SGPA calibrates transformer uncertainty for safety-critical tasks.
problem Uncertainty estimation in transformer models for safety-critical domains.
method Bayesian inference in transformer's output space using sparse Gaussian processes.
result SGPA-based Transformers improve in-distribution calibration and out-of-distribution robustness.
SC unifies ICL calibration methods and improves LLM performance.
problem Systematic biases in LLM predictions leading to unstable performance.
method Supervised Calibration (SC) learns optimal affine transformations in logit space.
result SC delivers state-of-the-art performance across multiple datasets.
A novel framework quantifies uncertainty using proper scores for various tasks.
problem Uncertainty quantification in machine learning for reliable applications.
method Proposes a general framework based on proper scores for epistemic, aleatoric uncertainty, and model calibration.
result Achieves state-of-the-art uncertainty estimation for large language models and generative models.
We study massless deformations of generalized calibrated cycles, which describe, in the language of generalized complex geometry, supersymmetric D-branes in N=1 supersymmetric compactifications with fluxes. We find that the deformations are classified by the first cohomology group of a Lie algebroid canonically associa…
Corrects bias in LLM-as-a-judge evaluations using adaptive calibration.
problem Bias in LLM evaluations due to imperfect sensitivity and specificity.
method Plug-in framework with confidence intervals accounting for test and calibration dataset uncertainties.
result LML-based evaluation yields more reliable estimates than human-only evaluation.
The paper introduces multicalibration to improve confidence scores in LLMs.
problem Improving the reliability and interpretability of confidence scores for LLMs.
method Forming groupings of prompt/completion pairs correlated with correctness, using clustering and self-annotation. Developing multicalibration algorithms to reduce overfitting.
result Our techniques yield confidence scores that significantly improve calibration and accuracy compared to existing methods.
DS-CP improves reliability of uncertainty quantification for large language models under domain shift.
problem Overconfident and factually incorrect outputs (hallucinations) from large language models.
method Adapts conformal prediction to large language models under domain shift by reweighting calibration samples.
result DS-CP delivers more reliable coverage than standard conformal prediction, especially under substantial distribution shifts.
Develops a power-calibrated framework for LLM watermarking, optimizing tradeoffs between detectability and distortion.
problem The trade-off between detectability and semantic distortion in logit-based watermarking.
method Power-calibrated statistical framework for watermark hyperparameters, establishing explicit relationships.
result Derives practical parameter selection procedures achieving optimal tradeoffs under constraints.
MACI improves LLM factuality inference with higher retention and lower time cost.
problem Ensuring factuality in LLM responses for high-stakes domains.
method Reformulated conformal inference in a multiplicative filtering setting, leveraging ensembles for more accurate factuality scores and group-conditional calibration.
result MACI achieves higher retention and lower time cost compared to baselines, preserving validity through group-conditional calibration.
Reduces false positives in classifying rare online platforms.
problem Challenges in accurately identifying rare online platforms with ML.
method Calibrated probabilities and ensembles to reduce bias.
result Significantly reduces false positives in rare event detection.
BayCANN uses ANN to speed up Bayesian calibration in health sciences.
problem Bayesian calibration's practical and computational burdens in health decision sciences.
method BayCANN trains an ANN metamodel to calibrate parameters probabilistically, comparing accuracy and speed to direct Bayesian calibration.
result BayCANN is more accurate and faster than direct Bayesian calibration methods.
FMP sampling improves model calibration without sharing data.
problem Difficulties in specifying priors for modern neural networks.
method FMP sampling replaces prior and likelihood with a predictive distribution, running the sampler centrally.
result FMP sampling significantly improves calibration over baseline methods.
PolySwarm uses a swarm of LLMs to predict and arbitrage prediction markets.
problem Real-time prediction market trading and latency arbitrage inefficiencies.
method PolySwarm employs a swarm of 50 diverse LLMs, Bayesian combination, and risk-controlled execution.
result Swarm aggregation outperforms single-model baselines in prediction tasks.
Extends FC-RAG to anytime-valid sequential coverage for language model swarms.
problem Maintain distribution-free coverage for a swarm of weak language models over time.
method Introduces Anytime-FC-RAG, a sequential extension with a summable calibration-deviation budget.
result Achieves time-uniform alarm validity and safety under predictable adaptive control.
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. Prototype model improves model auditing and understanding.
problem Auditing and understanding modern language models is expensive and approximate.
method Introduced a sparse, non-negative mixture of learned prototypes trained with clustering objectives.
result Prototype models either surpass or remain within 2.5 percentage points of dense baselines on downstream tasks.
Paper explores using LLMs for zero-shot reinforcement learning in continuous spaces.
problem Leveraging LLMs for continuous state spaces in reinforcement learning.
method Disentangled In-Context Learning (DICL) to handle multivariate data and control signal.
result DICL produces well-calibrated uncertainty estimates in reinforcement learning settings.
Feedback loops amplify dataset biases, affecting future model performance.
problem Feedback loops amplify biases in datasets, risking future model reliability.
method Formalized system where model interactions are recorded and reused, analyzed for bias amplification.
result Models that behave like samples from the training distribution are more stable and calibrated.
The paper accelerates LLM inference by adding early exit heads trained in a self-supervised manner.
problem Inference speed in large language models (LLMs) is slow and resource-intensive.
method Adding self-supervised early exit heads at intermediate transformer layers to stop computation early based on confidence thresholds.
result Entropy provides the most reliable confidence metric for stopping computation early.
LEWIS merges LLMs without training, improving performance on specific tasks.
problem Limited performance improvement of merged models on specific benchmarks.
method Guided model merging using layer-wise sparsity and task-vector pruning.
result Improved model performance by up to 11.3% on math-solving tasks.
Paper shows equivalence between two alignment methods and introduces a new algorithm.
problem Ensuring human alignment of large language models for useful, safe, and pleasant user experience.
method Introduces IPO-MD algorithm, showing equivalence between IPO and Nash-MD methods.
result Equivalence between IPO and Nash-MD methods proven when considering online version of IPO.
LLMs overestimate stock returns and are less accurate at predicting extreme outcomes.
problem Behavioral biases in LLMs' stock return forecasts.
method Comparison of LLM forecasts with crowd-sourced estimates and historical data.
result LLMs overestimate stock returns and are less accurate at predicting extreme outcomes.
Improved unsupervised probing for ranking tasks using Contrast-Consistent Ranking.
problem Improving self-consistency in language model rankings.
method Adapting Contrast-Consistent Search (CCS) to Contrast-Consistent Ranking (CCR) for ranking tasks.
result CCR probing outperforms prompting techniques across different models and datasets.
Study improves LLMs for PPI analysis by addressing uncertainty.
problem Uncertainty in LLM predictions for PPIs.
method Fine-tuned LLaMA-3 and BioMedGPT models, LoRA ensembles, Bayesian LoRA for UQ.
result Competitive PPI identification performance across diverse disease contexts.
Bayesian MoE framework improves LLMs' uncertainty detection.
problem Brittleness and overconfidence in deterministic routing of LLMs.
method Structured Bayesian routing in weight-space, logit-space, and selection-space.
result Significant improvements in routing stability, calibration, and OoD detection.