Copertina

Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tan, Hexiang, Sun, Fei, Liu, Sha, Su, Du, Cao, Qi, Chen, Xin, Wang, Jingang, Cai, Xunliang, Wang, Yuanzhuo, Shen, Huawei, Cheng, Xueqi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
di: Tan, Hexiang, et al.
Pubblicazione: (2024)

BaseCal: Unsupervised Confidence Calibration via Base Model Signals
di: Tan, Hexiang, et al.
Pubblicazione: (2026)

Fine-tuning Done Right in Model Editing
di: Yang, Wanli, et al.
Pubblicazione: (2025)

Fact-Level Confidence Calibration and Self-Correction
di: Yuan, Yige, et al.
Pubblicazione: (2024)

Qsnail: A Questionnaire Dataset for Sequential Question Generation
di: Lei, Yan, et al.
Pubblicazione: (2024)

AsarRec: Adaptive Sequential Augmentation for Robust Self-supervised Sequential Recommendation
di: Zhang, Kaike, et al.
Pubblicazione: (2025)

Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs
di: Yang, Wanli, et al.
Pubblicazione: (2026)

LoRec: Large Language Model for Robust Sequential Recommendation against Poisoning Attacks
di: Zhang, Kaike, et al.
Pubblicazione: (2024)

Personalized Denoising Implicit Feedback for Robust Recommender System
di: Zhang, Kaike, et al.
Pubblicazione: (2025)

Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System
di: Zhang, Kaike, et al.
Pubblicazione: (2024)

Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
di: Zhang, Kaike, et al.
Pubblicazione: (2024)

Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration
di: Wu, Kangxi, et al.
Pubblicazione: (2024)

The Mirage of Model Editing: Revisiting Evaluation in the Wild
di: Yang, Wanli, et al.
Pubblicazione: (2025)

Robust Recommender System: A Survey and Future Directions
di: Zhang, Kaike, et al.
Pubblicazione: (2023)

Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation
di: Gu, Jia, et al.
Pubblicazione: (2024)

Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism
di: Liu, Jiahao, et al.
Pubblicazione: (2024)

Understanding the Collapse of LLMs in Model Editing
di: Yang, Wanli, et al.
Pubblicazione: (2024)

Ltri-LLM: Streaming Long Context Inference for LLMs with Training-Free Dynamic Triangular Attention Pattern
di: Tang, Hongyin, et al.
Pubblicazione: (2024)

Consistency Matters: Explore LLMs Consistency From a Black-Box Perspective
di: Zhao, Fufangchen, et al.
Pubblicazione: (2024)

Unlink to Unlearn: Simplifying Edge Unlearning in GNNs
di: Tan, Jiajun, et al.
Pubblicazione: (2024)

Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection
di: Wang, Pei, et al.
Pubblicazione: (2024)

Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
di: Ding, Hanxing, et al.
Pubblicazione: (2024)

IDEA: Invariant Defense for Graph Adversarial Robustness
di: Tao, Shuchang, et al.
Pubblicazione: (2023)

Estimating the Self-Consistency of LLMs
di: Nowak, Robert
Pubblicazione: (2025)

TEA: Test-time Energy Adaptation
di: Yuan, Yige, et al.
Pubblicazione: (2023)

Sub-Scaling Laws: On the Role of Data Density and Training Strategies in LLMs
di: Chen, Zhengyu, et al.
Pubblicazione: (2025)

BotTrans: A Multi-Source Graph Domain Adaptation Approach for Social Bot Detection
di: Shi, Boshen, et al.
Pubblicazione: (2025)

Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets
di: Jiang, Xuhui, et al.
Pubblicazione: (2023)

LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models
di: Zhao, Shilong, et al.
Pubblicazione: (2025)

Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data
di: Zhang, Xuemiao, et al.
Pubblicazione: (2025)

SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models
di: Diao, Muxi, et al.
Pubblicazione: (2024)

FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy
di: Zhang, Xuemiao, et al.
Pubblicazione: (2025)

A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
di: Xu, Shicheng, et al.
Pubblicazione: (2024)

Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement
di: Hou, Danyang, et al.
Pubblicazione: (2024)

D-Models and E-Models: Diversity-Stability Trade-offs in the Sampling Behavior of Large Language Models
di: Gu, Jia, et al.
Pubblicazione: (2026)

Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue
di: Zhou, Junkai, et al.
Pubblicazione: (2023)

Event-aware Video Corpus Moment Retrieval
di: Hou, Danyang, et al.
Pubblicazione: (2024)

InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning
di: Wang, Zixu, et al.
Pubblicazione: (2025)

Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems
di: Wang, Zixu, et al.
Pubblicazione: (2026)

Negative as Positive: Enhancing Out-of-distribution Generalization for Graph Contrastive Learning
di: Wang, Zixu, et al.
Pubblicazione: (2024)