Copertina

Differentiable Conformal Training for LLM Reasoning Factuality

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hittesdorf, Nathan, Salzetta, Marco, Cheng, Lu
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Conformal Language Model Reasoning with Coherent Factuality
di: Rubin-Toles, Maxon, et al.
Pubblicazione: (2025)

Language Models with Conformal Factuality Guarantees
di: Mohri, Christopher, et al.
Pubblicazione: (2024)

Online Conformal Abstention for Factuality Control Under Adversarial Bandit Feedback
di: Lee, Minjae, et al.
Pubblicazione: (2025)

Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning
di: Zhou, Cai, et al.
Pubblicazione: (2026)

Conformal Linguistic Calibration: Trading-off between Factuality and Specificity
di: Jiang, Zhengping, et al.
Pubblicazione: (2025)

Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling
di: Ye, Kai, et al.
Pubblicazione: (2026)

Differentially Private Conformal Prediction
di: Wu, Jiamei, et al.
Pubblicazione: (2026)

Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning
di: Gai, Jingchu, et al.
Pubblicazione: (2025)

Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models
di: Rubashevskii, Aleksandr, et al.
Pubblicazione: (2026)

Learning Marked Temporal Point Process Explanations based on Counterfactual and Factual Reasoning
di: Liu, Sishun, et al.
Pubblicazione: (2025)

Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic Insights
di: Chen, Yi, et al.
Pubblicazione: (2026)

SIFiD: Reassess Summary Factual Inconsistency Detection with LLM
di: Yang, Jiuding, et al.
Pubblicazione: (2024)

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
di: Yang, Junxiao, et al.
Pubblicazione: (2025)

Conformal Risk Training: End-to-End Optimization of Conformal Risk Control
di: Yeh, Christopher, et al.
Pubblicazione: (2025)

Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding
di: Gao, Chufan, et al.
Pubblicazione: (2025)

Conformalized Link Prediction on Graph Neural Networks
di: Zhao, Tianyi, et al.
Pubblicazione: (2024)

MALT: Improving Reasoning with Multi-Agent LLM Training
di: Motwani, Sumeet Ramesh, et al.
Pubblicazione: (2024)

Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomy
di: Xu, Liyan, et al.
Pubblicazione: (2024)

Who's Asking? Evaluating LLM Robustness to Inquiry Personas in Factual Question Answering
di: Akpinar, Nil-Jana, et al.
Pubblicazione: (2025)

Privacy-Preserving Conformal Prediction Under Local Differential Privacy
di: Penso, Coby, et al.
Pubblicazione: (2025)

SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
di: Zhou, Yifei, et al.
Pubblicazione: (2025)

PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning
di: Kachuee, Mohammad, et al.
Pubblicazione: (2025)

Knowing but Not Correcting: Routine Task Requests Suppress Factual Correction in LLMs
di: Chen, Zixuan, et al.
Pubblicazione: (2026)

Beyond Data Splitting: Full-Data Conformal Prediction by Differential Privacy
di: Cho, Young Hyun, et al.
Pubblicazione: (2026)

NextMem: Towards Latent Factual Memory for LLM-based Agents
di: Zhang, Zeyu, et al.
Pubblicazione: (2026)

Counterfactual Fairness by Combining Factual and Counterfactual Predictions
di: Zhou, Zeyu, et al.
Pubblicazione: (2024)

RAC: Efficient LLM Factuality Correction with Retrieval Augmentation
di: Li, Changmao, et al.
Pubblicazione: (2024)

Cost-Sensitive Conformal Training with Provably Controllable Learning Bounds
di: Jia, Xuesong, et al.
Pubblicazione: (2025)

On Training-Conditional Conformal Prediction and Binomial Proportion Confidence Intervals
di: Coppola, Rudi, et al.
Pubblicazione: (2025)

Leveraging Continuously Differentiable Activation Functions for Learning in Quantized Noisy Environments
di: Shah, Vivswan, et al.
Pubblicazione: (2024)

Incompressible Knowledge Probes: Estimating Black-Box LLM Parameter Counts via Factual Capacity
di: Li, Bojie
Pubblicazione: (2026)

Knowledge Graph-Assisted LLM Post-Training for Enhanced Legal Reasoning
di: Song, Dezhao, et al.
Pubblicazione: (2026)

Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning
di: Azizi, Seyedarmin, et al.
Pubblicazione: (2026)

Class Adaptive Conformal Training
di: Marani, Badr-Eddine, et al.
Pubblicazione: (2026)

SABER: Switchable and Balanced Training for Efficient LLM Reasoning
di: Zhao, Kai, et al.
Pubblicazione: (2025)

Native Reasoning Models: Training Language Models to Reason on Unverifiable Data
di: Wang, Yuanfu, et al.
Pubblicazione: (2026)

DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning
di: Zhao, Hanyang, et al.
Pubblicazione: (2025)

DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability
di: He, Yunzhen, et al.
Pubblicazione: (2025)

Multi-LLM Adaptive Conformal Inference for Reliable LLM Responses
di: Noh, Kangjun, et al.
Pubblicazione: (2026)

Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty
di: Pang, Lingyou, et al.
Pubblicazione: (2025)