LLMs struggle with zero-shot annotation tasks due to model-internalized priors.
problem Impact of model-internalized priors on LLM performance in zero-shot annotation tasks.
method Investigated three dimensions: familiarity, decision stickiness, and susceptibility to misaligned task definitions.
result Nearly two-thirds of zero-shot errors are resistant to correction, with a rescue rate of 34.8%. Definition-Specific Familiarity (DSF) shows a positive association with model performance.
Fine-tunes LLMs to correct bias in predictions.
problem LLMs exhibit bias in predictions from data.
method Supervised fine-tuning with Low-Rank Adaptation (LoRA).
result Fine-tuning corrects bias in both controlled and real-world settings.
LaTRO optimizes latent reasoning in LLMs without external reward.
problem Training LLMs to perform complex reasoning tasks.
method Formulates reasoning as latent distribution sampling and optimizes via variational approaches.
result LLMs improve reasoning and evaluation quality through self-improvement.
LOLA uses LLMs to optimize content delivery, outperforming traditional methods.
problem Identifying the most engaging headlines for user engagement.
method LOLA integrates LLMs with adaptive experimentation to optimize content delivery.
result LOLA outperforms traditional methods in optimizing user engagement.
Improved text generation with discourse-aware soft prompts.
problem Efficient fine-tuning methods don't generalize across all generation tasks.
method Hierarchical blocking and attention sparsity on prefix parameters.
result Structured design of prefix parameters yields more coherent generations.
Study finds LLMs hallucinate in finance tasks, needing research.
problem Hallucination in LLMs in finance.
method Empirical investigation of four methods to mitigate hallucination.
result LLMs hallucinate in financial tasks.
New framework improves interpretability of trainable prompts.
problem Improving task-specific LLM performance with soft prompts remains a black-box method.
method Developed a theoretical framework for evaluating interpretability of trainable prompts, inspired new objective functions.
result Found a fundamental trade-off between interpretability and task performance in trainable prompts.
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.
CurveRL optimizes large model reasoning by reweighting prompts based on their rank and density.
problem Improving large language model reasoning through context reweighting.
method Formulated prompt reweighting as a functional derivative, proposing CurveRL based on quantile coordinate transform.
result CurveRL consistently outperforms existing methods across multiple benchmarks.
ICON learns differential equation operators from prompts, reducing retraining and improving few-shot learning.
problem Training neural networks to solve differential equations without retraining for new problems.
method In-Context Operator Networks (ICON) that learns operators from prompted data and applies them to new problems.
result ICON can generalize to new operators beyond the training distribution and requires only a few demos.
PPO optimizes LLM-generated alpha weights for better trading performance.
problem Adapting LLM-generated alphas for varying market conditions.
method Proximal Policy Optimization (PPO) for dynamic alpha weight adjustment.
result PPO-optimized strategy achieves higher Sharpe ratios and smaller drawdowns.
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.
Non-intrusive algorithm corrects corrupted data in classification models.
problem Classification problems with corrupted training data.
method Post-processes a trained classification model with a correction procedure.
result Corrected models deliver correct classification results even with corrupted data.
Unified Bayesian model explains in-context learning and activation steering in LLMs.
problem Understanding and controlling the behavior of large language models (LLMs) through prompts and activations.
method Developed a Bayesian model to explain and predict the effects of in-context learning and activation steering.
result Unified model predicts distinct phases and sudden shifts in LLM behavior, explaining prior empirical phenomena.
Casper uses causal graph neural networks to improve spatiotemporal time series imputation.
problem Imputing missing values in spatiotemporal time series with confounders and non-causal correlations.
method Casper introduces a novel Prompt Based Decoder (PBD) and Spatiotemporal Causal Attention (SCA) to block confounders and discover causal relationships.
result Casper outperforms baselines and effectively discovers causal relationships in spatiotemporal time series imputation.
A new model of learning corrects for chance to improve learning outcomes.
problem The importance of chance-corrected measures in learning.
method Developed two models: Informatron and AdaBook, based on empirical psychological results.
result Chance correction facilitates learning, as shown by computational results.
Mathematical study of instanton corrected q-map spaces and their isometries.
problem Understanding the isometries of instanton corrected q-map spaces.
method Study of isometries of instanton corrected q-map spaces associated to PSR manifolds.
result Explicit example of instanton corrected q-map space with full SL(2,Z) acting by isometries.
Corrected misstatements about invariant rank in ECS manifold papers.
problem Misstated invariant rank (d=1 instead of d=2) in several papers on ECS manifolds.
method Identified the class of examples with d=1, explained why d=2, and listed corrections.
result Corrected papers to accurately state d=2 for ECS manifolds.
New method combines machine learning with data assimilation for model error correction.
problem Correcting model errors using sparse and noisy observations.
method Hybrid machine learning and data assimilation methods.
result Tendency correction outperforms resolvent correction in data assimilation experiments.
Localized Multidirectional Correction improves non-refusal target-response behavior in foundation models.
problem Controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models.
method Introduce Localized Multidirectional Correction (LoMC), a support-gated intervention framework.
result Substantially improves non-refusal target-response behavior while maintaining general capability under a compact intervention footprint.
Theoretical analysis shows LLMs can self-correct responses through in-context learning.
problem Understanding how large language models improve through self-correction.
method Theoretical analysis based on simplified alignment task, focusing on softmax attention, multi-head attention, and MLP blocks.
result LLMs can refine responses in an in-context way when given accurate self-examinations as rewards.
New algorithms improve boosting by optimizing chance-corrected measures.
problem Improving boosting algorithms to use chance-corrected measures effectively.
method Developed new algorithms (AdaBook and Multibook) that optimize chance-corrected measures.
result AdaBook and Multibook outperform standard Multiboost or AdaBoost in multiclass situations.
Study examines corrections to heterotic geometry on SU(3) manifolds.
problem Analyzing α′2 corrections to heterotic supersymmetry algebra. method Derives integrability condition and pure gauge correction from graviton equation of motion.
result Curvature of tangent bundle connection acquires a (0,2) component, disrupting semi-classical intuition.
Painless Activation Steering automates post-training for LMs without manual intervention.
problem Manual post-training methods are time-consuming and labor-intensive.
method Painless Activation Steering (PAS) is a fully automated approach that requires no manual intervention.
result PAS reliably improves performance for behavior tasks but not for intelligence-oriented tasks.
A model corrects Lithuanian grammatical errors.
problem Lack of language skills and typing errors in Lithuanian.
method Transformer architectures for subword and byte-level approaches.
result F0.5=0.92 for Lithuanian grammatical error correction. Expectation Propagation (EP) provides a framework for approximate inference. When the model under consideration is over a latent Gaussian field, with the approximation being Gaussian, we show how these approximations can systematically be corrected. A perturbative expansion is made of the exact but intractable correcti…
MaxEnt Model Correction improves reinforcement learning model accuracy.
problem Improving reinforcement learning model accuracy and convergence.
method MaxEnt Model Correction (MoCo) procedure to correct model's next-state distributions.
result MoCoVI and MoCoDyna algorithms converge faster and effectively use approximate models.
We derive a closed formula for the Heegaard Floer correction terms of lens spaces in terms of the classical Dedekind sum and its generalization, the Dedekind-Rademacher sum. Our proof relies on a reciprocity formula for the correction terms established by Ozsvath and Szabo. A consequence of our result is that the Casso…
New methods correct spectral distortions using known analyte concentrations.
problem Distorted spectral shapes from absorbing and scattering contributions.
method Modified penalized baseline correction methods that incorporate known analyte concentrations.
result Improved prediction performance on near infra-red data sets.
This is a corrected version of our paper published in Osaka Journal of Mathematics 51(2014), 673-693. We correct Theorem~1.1, Proposition~3.3 and their proofs.
Bayesian method corrects for model selection multiplicity in regression.
problem Model selection multiplicity in regression analysis.
method Developed a Bayesian prior distribution based on Holm procedure analogy.
result Adequate multiplicity correction requires sparsity not provided by recommended priors.
In recent years several trading platforms appeared which provide a backtest engine to calculate historic performance of self designed trading strategies on underlying candle data. The construction of a correct working backtest engine is, however, a subtle task as shown by Maier-Paape and Platen (cf. arXiv:1412.5558 [q-…
This paper corrects the proof of the Theorem 2 from the Gower's paper \cite[page 5]{Gower:1982} as well as corrects the Theorem 7 from Gower's paper \cite{Gower:1986}. The first correction is needed in order to establish the existence of the kernel function used commonly in the kernel trick e.g. for k-means clusterin…
New approach shows AI can adapt like toddlers by correcting old knowledge.
problem Lack of adaptability in AI models compared to humans and animals.
method Casting adaptation as posterior correction and using Bayesian Learning Rule.
result AI can learn to adapt quickly by using posterior correction.
Khovanov homology helps create quantum error-correcting codes.
problem Creating robust quantum error-correcting codes.
method Using Khovanov homology and its extensions to define and analyze quantum codes.
result New families of quantum codes with desirable properties.
The study examines methods to correct measurement error in nutritional epidemiology studies.
problem Measurement error in nutritional studies leads to biased and underconfident estimates.
method The article reviews various bias-correction models for exposure variables in nutritional epidemiology.
result Bias-correction methods are essential for accurate inference in nutritional studies.
Post-training corrections boost time-series forecasting accuracy.
problem Improving forecasting accuracy of large models after training.
method Sequential application of carefully selected corrections to predictions.
result Up to 30% improvement in forecasting accuracy with minimal overhead.
This paper improves deep learning model consistency through ensemble methods.
problem Consistency and correct-consistency issues in deep learning models.
method Formal definition of consistency and correct-consistency, proving ensemble improvement, proposing dynamic snapshot ensemble method.
result Ensemble methods can improve correct-consistency of deep learning models.
UCPO improves diversity in reinforcement learning models, maintaining high accuracy.
problem RLVR objectives often lead to diversity collapse, reducing coverage of correct solutions.
method UCPO adds a conditional uniformity penalty to GRPO, redistributing probability mass.
result UCPO improves Pass@K and diversity while maintaining competitive Pass@1 accuracy.
Leveraging weak or noisy supervision for building effective machine learning models has long been an important research problem. Its importance has further increased recently due to the growing need for large-scale datasets to train deep learning models. Weak or noisy supervision could originate from multiple sources i…
Large language models struggle with causal relationships, leading to biases and hallucinations.
problem LLMs struggle with true causal relationships, leading to biases and hallucinations.
method Embed causality into LLMs training process at every stage.
result LLMs need to be trained to understand and apply causal knowledge, not just recite it.
This paper corrects climate model biases using a factor model approach.
problem Systematic biases in GCM outputs due to unobserved confounders.
method Factor model approach to learn latent confounders from historical data and apply them to enhance bias correction.
result Significant improvements in the accuracy of precipitation outputs.
We present a general formalism for incorporating the string corrections in generalised geometry, which necessitates the extension of the generalised tangent bundle. Not only are such extensions obstructed, string symmetries and the existence of a well-defined effective action require a precise choice of the (generalise…
There is a gap in the proof of the main theorem in the article [ShCh13a] on optimal bounds for the Morse lemma in Gromov-hyperbolic spaces. We correct this gap, showing that the main theorem of [ShCh13a] is correct. We also describe a computer certification of this result.
Paper addresses hypothesis space misspecification in learning from human demonstrations and corrections.
problem Hypothesis space misspecification in learning from human demonstrations and corrections.
method Reason explicitly about how well the robot can explain human inputs given its hypothesis space.
result Demonstrates method on a 7 DOF robot manipulator.
The paper proves an obstruction to immersed curves with specific curvature.
problem Existence of immersed curves with prescribed curvature.
method Proofs and corrections of submitted manuscript.
result An obstruction to the existence of immersed curves of prescribed curvature.
The paper examines when importance weighting is needed for nonparametric and misspecified models.
problem When is importance weighting correction needed for covariate shift adaptation?
method Analysis of IW-corrected kernel ridge regression in various settings.
result The importance weighting correction is needed for nonparametric and misspecified models to obtain the best approximation of the true unknown function.
DisCor corrects reinforcement learning issues by re-weighting collected data.
problem Reinforcement learning algorithms struggle with instability and sensitivity to hyperparameters.
method DisCor reweights collected data to mitigate issues caused by the distribution of experience.
result DisCor improves reinforcement learning in challenging settings like multi-task learning and noisy reward signals.