Image de couverture de livre

SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shen, William F., Qiu, Xinchi, Cancedda, Nicola, Lane, Nicholas D.
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective
par: Qiu, Xinchi, et autres
Publié: (2024)

LLM Unlearning via Neural Activation Redirection
par: Shen, William F., et autres
Publié: (2025)

Spectral Filters, Dark Signals, and Attention Sinks
par: Cancedda, Nicola
Publié: (2024)

APrompt4EM: Augmented Prompt Tuning for Generalized Entity Matching
par: Xia, Yikuan, et autres
Publié: (2024)

Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
par: Wannan, et autres
Publié: (2025)

MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates
par: Iacob, Alex, et autres
Publié: (2025)

Gradient-less Federated Gradient Boosting Trees with Learnable Learning Rates
par: Ma, Chenyang, et autres
Publié: (2023)

LoRDO: Distributed Low-Rank Optimization with Infrequent Communication
par: Jovanović, Andrej, et autres
Publié: (2026)

Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts
par: Koishekenov, Yeskendir, et autres
Publié: (2025)

Knowledge Graph Guided Evaluation of Abstention Techniques
par: Vasisht, Kinshuk, et autres
Publié: (2024)

DCGL: Dual-Channel Graph Learning with Large Language Models for Knowledge-Aware Recommendation
par: Zou, Xinchi, et autres
Publié: (2026)

Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
par: Abdaljalil, Samir, et autres
Publié: (2026)

Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery
par: Clark, Nicholas, et autres
Publié: (2025)

I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation
par: Zong, Haotian, et autres
Publié: (2026)

Semantic Reward Collapse and the Preservation of Epistemic Integrity in Adaptive AI Systems
par: Parris, William
Publié: (2026)

The Future of Large Language Model Pre-training is Federated
par: Sani, Lorenzo, et autres
Publié: (2024)

Verifying Chain-of-Thought Reasoning via Its Computational Graph
par: Zhao, Zheng, et autres
Publié: (2025)

Soft-Label Training Preserves Epistemic Uncertainty
par: Singh, Agamdeep, et autres
Publié: (2025)

Faithful Path Language Modeling for Explainable Recommendation over Knowledge Graph
par: Balloccu, Giacomo, et autres
Publié: (2023)

Cost-Saving LLM Cascades with Early Abstention
par: Zellinger, Michael J., et autres
Publié: (2025)

Reliable Text-to-SQL with Adaptive Abstention
par: Chen, Kaiwen, et autres
Publié: (2025)

Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation
par: Radharapu, Bhaktipriya, et autres
Publié: (2025)

From Entity-Centric to Goal-Oriented Graphs: Enhancing LLM Knowledge Retrieval in Minecraft
par: Leung, Jonathan, et autres
Publié: (2025)

Computational Compliance for AI Regulation: Blueprint for a New Research Domain
par: Marino, Bill, et autres
Publié: (2026)

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
par: Kirichenko, Polina, et autres
Publié: (2025)

On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation
par: Galozy, Alexander
Publié: (2026)

Augmenting Safety-Critical Driving Scenarios while Preserving Similarity to Expert Trajectories
par: Mirkhani, Hamidreza, et autres
Publié: (2024)

DERA: Dense Entity Retrieval for Entity Alignment in Knowledge Graphs
par: Wang, Zhichun, et autres
Publié: (2024)

Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
par: Gourabathina, Abinitha, et autres
Publié: (2026)

Improving LLM Reliability through Hybrid Abstention and Adaptive Detection
par: Sharma, Ankit, et autres
Publié: (2026)

Auditable Decision Models with Learned Abstention and Real-Time Steering
par: Chandrasekaran, Sankaranarayanan Palamadai
Publié: (2026)

Knowledge Graph Extension by Entity Type Recognition
par: Shi, Daqian
Publié: (2024)

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
par: Ferrando, Javier, et autres
Publié: (2024)

Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks
par: Shen, William F., et autres
Publié: (2026)

Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models
par: Liu, Xinxin, et autres
Publié: (2024)

Named Entity Recognition in COVID-19 tweets with Entity Knowledge Augmentation
par: Zhang, Xuankang, et autres
Publié: (2025)

Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context
par: Chen, Jianfang, et autres
Publié: (2025)

An Epistemic Perspective on Agent Awareness
par: Naumov, Pavel, et autres
Publié: (2025)

Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities
par: Zhao, Ze, et autres
Publié: (2026)

Bounded-Abstention Pairwise Learning to Rank
par: Ferrara, Antonio, et autres
Publié: (2025)