UQ4CT integrates functional-level uncertainty calibration into mixture-of-experts LoRA fine-tuning via a dedicated loss, cutting expected calibration error by over 25% on multiple-choice and generative QA tasks.
Lora ensembles for large language model fine-tuning.arXiv preprint arXiv:2310.00035
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
verdicts
UNVERDICTED 11representative citing papers
Spectral Souping learns offline specialized policies for fine-grained preferences and merges them online using a discovered universal spectral representation for efficient LLM alignment.
UG-TTT adds epistemic uncertainty measured by adapter disagreement as an exploration bonus in RL for LLMs, raising maximum reward and diversity on scientific discovery benchmarks.
BaLoRA is a Bayesian LoRA variant with input-adaptive noise that improves accuracy over standard LoRA and supplies well-calibrated uncertainty estimates on language, vision, and scientific prediction tasks.
Cross-model semantic disagreement adds an epistemic uncertainty term that improves total uncertainty estimation over self-consistency alone, helping flag confident errors in LLMs.
Succinct Model Difference Proofs certify that a neural-network update stays inside a policy-defined drift class using zero-knowledge proofs whose cost depends only on the drift structure.
PoLAR-VBLL combines orthogonalized low-rank adapters with variational Bayesian last-layer inference to enable scalable, well-calibrated uncertainty quantification in fine-tuned LLMs.
Introduces a Bayesian framework viewing LLM prompts as textual parameters and proposes MHLP, a novel MCMC algorithm using LLM proposals, to perform inference and improve accuracy plus uncertainty quantification on benchmarks.
BaRA adds Bayesian adaptive rank allocation to LoRA fine-tuning by activating sparse instance-specific latent factors, with a generalization bound depending on learned joint effective rank rather than fixed maximum rank.
Conf-Gen adapts conformal risk control to generative tasks by relaxing assumptions, unifying prior CP work on LLMs and extending guarantees to image generators, conversational AI, and AI agent correctness.
Fine-tuned small language models trained on a synthetic Windows event log dataset with remediation steps outperform larger models in issue detection and solution generation with lower computational cost.
citing papers explorer
-
Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs
UQ4CT integrates functional-level uncertainty calibration into mixture-of-experts LoRA fine-tuning via a dedicated loss, cutting expected calibration error by over 25% on multiple-choice and generative QA tasks.
-
Spectral Souping: A Unified Framework for Online Preference Alignment
Spectral Souping learns offline specialized policies for fine-grained preferences and merges them online using a discovered universal spectral representation for efficient LLM alignment.
-
Epistemic Uncertainty for Test-Time Discovery
UG-TTT adds epistemic uncertainty measured by adapter disagreement as an exploration bonus in RL for LLMs, raising maximum reward and diversity on scientific discovery benchmarks.
-
BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models
BaLoRA is a Bayesian LoRA variant with input-adaptive noise that improves accuracy over standard LoRA and supplies well-calibrated uncertainty estimates on language, vision, and scientific prediction tasks.
-
Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification
Cross-model semantic disagreement adds an epistemic uncertainty term that improves total uncertainty estimation over self-consistency alone, helping flag confident errors in LLMs.
-
Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates
Succinct Model Difference Proofs certify that a neural-network update stays inside a policy-defined drift class using zero-knowledge proofs whose cost depends only on the drift structure.
-
Scalable Variational Bayesian Fine-Tuning of LLMs via Orthogonalized Low-Rank Adapters
PoLAR-VBLL combines orthogonalized low-rank adapters with variational Bayesian last-layer inference to enable scalable, well-calibrated uncertainty quantification in fine-tuned LLMs.
-
Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems
Introduces a Bayesian framework viewing LLM prompts as textual parameters and proposes MHLP, a novel MCMC algorithm using LLM proposals, to perform inference and improve accuracy plus uncertainty quantification on benchmarks.
-
BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning
BaRA adds Bayesian adaptive rank allocation to LoRA fine-tuning by activating sparse instance-specific latent factors, with a generalization bound depending on learned joint effective rank rather than fixed maximum rank.
-
Conf-Gen: Conformal Uncertainty Quantification for Generative Models
Conf-Gen adapts conformal risk control to generative tasks by relaxing assumptions, unifying prior CP work on LLMs and extending guarantees to image generators, conversational AI, and AI agent correctness.
-
Fine-Tuning Small Language Models for Solution-Oriented Windows Event Log Analysis
Fine-tuned small language models trained on a synthetic Windows event log dataset with remediation steps outperform larger models in issue detection and solution generation with lower computational cost.