Copertina

Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Da, Longchao, Liu, Xiaoou, Dai, Jiaxin, Cheng, Lu, Wang, Yaqing, Wei, Hua
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Symbolic Computation 68T50, 68T37, 68Q32 I.2.7; I.2.6; I.2.4
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering
di: Chen, Tiejin, et al.
Pubblicazione: (2026)

Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
di: Liu, Xiaoou, et al.
Pubblicazione: (2026)

Answer Set Networks: Casting Answer Set Programming into Deep Learning
di: Skryagin, Arseny, et al.
Pubblicazione: (2024)

D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree
di: Lei, Xiang, et al.
Pubblicazione: (2025)

GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs
di: Da, Longchao, et al.
Pubblicazione: (2025)

Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval
di: Haque, Md. Asraful, et al.
Pubblicazione: (2026)

Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning
di: Zhang, Li, et al.
Pubblicazione: (2025)

Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies)
di: Beliaeva, Aleksandra, et al.
Pubblicazione: (2025)

LTL Verification of Memoryful Neural Agents
di: Hosseini, Mehran, et al.
Pubblicazione: (2025)

Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free
di: Zhang, Li, et al.
Pubblicazione: (2026)

Towards Probabilistic Question Answering Over Tabular Data
di: Shen, Chen, et al.
Pubblicazione: (2025)

CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density
di: Kaiser, Daniel, et al.
Pubblicazione: (2025)

Modularity in Transformers: Investigating Neuron Separability & Specialization
di: Pochinkov, Nicholas, et al.
Pubblicazione: (2024)

Neuro-Symbolic Process Anomaly Detection
di: Gaikwad, Devashish, et al.
Pubblicazione: (2026)

Error Detection and Constraint Recovery in Hierarchical Multi-Label Classification without Prior Knowledge
di: Kricheli, Joshua Shay, et al.
Pubblicazione: (2024)

On measuring grounding and generalizing grounding problems
di: Quigley, Daniel, et al.
Pubblicazione: (2025)

Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining
di: Cao, Deyu, et al.
Pubblicazione: (2025)

JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vector Manipulation
di: Huang, Yingbing, et al.
Pubblicazione: (2025)

Do LLMs Truly Understand When a Precedent Is Overruled?
di: Zhang, Li, et al.
Pubblicazione: (2025)

CELI: Controller-Embedded Language Model Interactions
di: Wagner, Jan-Samuel, et al.
Pubblicazione: (2024)

InhibiDistilbert: Knowledge Distillation for a ReLU and Addition-based Transformer
di: Zhang, Tony, et al.
Pubblicazione: (2025)

SUBMASSIVE: Resolving Subclass Cycles in Very Large Knowledge Graphs
di: Wang, Shuai, et al.
Pubblicazione: (2024)

Rethinking the Multilingual Reasoning Gap with Layer Swap
di: Lasbordes, Maxence, et al.
Pubblicazione: (2026)

BMAM: Brain-inspired Multi-Agent Memory Framework
di: Li, Yang, et al.
Pubblicazione: (2026)

Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis
di: Amamou, Hazem, et al.
Pubblicazione: (2026)

Kodezi Chronos: A Debugging-First Language Model for Repository-Scale Code Understanding
di: Khan, Ishraq, et al.
Pubblicazione: (2025)

Deterministic Event-Graph Substrates as World Models for Counterfactual Reasoning
di: Rovai, Fabio
Pubblicazione: (2026)

CLMN: Concept based Language Models via Neural Symbolic Reasoning
di: Yang, Yibo
Pubblicazione: (2025)

Aligning LLMs for Multilingual Consistency in Enterprise Applications
di: Agarwal, Amit, et al.
Pubblicazione: (2025)

Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning
di: Pather, Kaviraj, et al.
Pubblicazione: (2025)

Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration
di: Lin, Shuhang, et al.
Pubblicazione: (2026)

Rule Extraction in Machine Learning: Chat Incremental Pattern Constructor
di: Nwokocha, Caleb Princewill
Pubblicazione: (2022)

Sliced-Wasserstein Distribution Alignment Loss Improves the Ultra-Low-Bit Quantization of Large Language Models
di: Cao, Deyu, et al.
Pubblicazione: (2026)

Separate Before You Compress: The WWHO Tokenization Architecture
di: Darshana, Kusal
Pubblicazione: (2026)

Normative Conditional Reasoning as a Fragment of HOL
di: Parent, Xavier, et al.
Pubblicazione: (2023)

MVTamperBench: Evaluating Robustness of Vision-Language Models
di: Agarwal, Amit, et al.
Pubblicazione: (2024)

How much do LLMs learn from negative examples?
di: Hamdan, Shadi, et al.
Pubblicazione: (2025)

NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution
di: Breneur, Oleksandr Marchenko, et al.
Pubblicazione: (2026)

Superior Scoring Rules for Probabilistic Evaluation of Single-Label Multi-Class Classification Tasks
di: Ahmadian, Rouhollah, et al.
Pubblicazione: (2024)

An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT
di: Ma, Chong, et al.
Pubblicazione: (2023)