Image de couverture de livre

Open Problems and a Hypothetical Path Forward in LLM Knowledge Paradigms

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ye, Xiaotian, Zhang, Mengqi, Wu, Shu
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning
par: Ye, Xiaotian, et autres
Publié: (2026)

LLM Unlearning Should Be Form-Independent
par: Ye, Xiaotian, et autres
Publié: (2025)

Knowledge Graph Enhanced Large Language Model Editing
par: Zhang, Mengqi, et autres
Publié: (2024)

Uncovering Entity Identity Confusion in Multimodal Knowledge Editing
par: Wu, Shu, et autres
Publié: (2026)

UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets
par: Wang, Wenyu, et autres
Publié: (2025)

Uncovering Context Reliance in Unstructured Knowledge Editing
par: Zhou, Zisheng, et autres
Publié: (2026)

Uncovering Overfitting in Large Language Model Editing
par: Zhang, Mengqi, et autres
Publié: (2024)

Disentangling Knowledge Representations for Large Language Model Editing
par: Zhang, Mengqi, et autres
Publié: (2025)

Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion
par: Yoon, Yejun, et autres
Publié: (2025)

Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse
par: Zhang, Chi, et autres
Publié: (2026)

LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements
par: Basmov, Victoria, et autres
Publié: (2024)

Bounded Path Context: A Controlled Study of Visible Path History in LLM-Based Knowledge Graph Question Answering
par: Shan, Xihang, et autres
Publié: (2026)

We Need Knowledge Distillation for Solving Math Word Problems
par: Shen, Zhenquan, et autres
Publié: (2025)

Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing
par: Zhang, Mengqi, et autres
Publié: (2024)

AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses
par: Lu, Xiaotian, et autres
Publié: (2024)

Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM
par: Chang, Haw-Shiuan, et autres
Publié: (2024)

Learning Domain-Invariant Features for Out-of-Context News Detection
par: Gu, Yimeng, et autres
Publié: (2024)

MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors
par: Luo, Xiaotian, et autres
Publié: (2026)

Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs
par: Xiao, Yilin, et autres
Publié: (2025)

Steel-LLM:From Scratch to Open Source -- A Personal Journey in Building a Chinese-Centric LLM
par: Gu, Qingshui, et autres
Publié: (2025)

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
par: Zhang, Yi-Fan, et autres
Publié: (2025)

Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation
par: Li, Changcheng, et autres
Publié: (2026)

Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing
par: Zhang, Yi-Kai, et autres
Publié: (2025)

HypoTermQA: Hypothetical Terms Dataset for Benchmarking Hallucination Tendency of LLMs
par: Uluoglakci, Cem, et autres
Publié: (2024)

Leveraging LLMs for Hypothetical Deduction in Logical Inference: A Neuro-Symbolic Approach
par: Li, Qingchuan, et autres
Publié: (2024)

Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving
par: Zhang, Xinyu, et autres
Publié: (2026)

Chart-HQA: A Benchmark for Hypothetical Question Answering in Charts
par: Chen, Xiangnan, et autres
Publié: (2025)

Can LLM be a Good Path Planner based on Prompt Engineering? Mitigating the Hallucination for Path Planning
par: Deng, Hourui, et autres
Publié: (2024)

Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoning
par: Zheng, Danna, et autres
Publié: (2024)

3D-Properties: Identifying Challenges in DPO and Charting a Path Forward
par: Yan, Yuzi, et autres
Publié: (2024)

LLM4CD: Leveraging Large Language Models for Open-World Knowledge Augmented Cognitive Diagnosis
par: Zhang, Weiming, et autres
Publié: (2025)

From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascades
par: Wu, Yu, et autres
Publié: (2025)

Using LLMs for Knowledge Component-level Correctness Labeling in Open-ended Coding Problems
par: Duan, Zhangqi, et autres
Publié: (2026)

Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation
par: Shang, Wenbo, et autres
Publié: (2024)

LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation
par: Wu, Haihang
Publié: (2024)

Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents
par: Zhou, Heng, et autres
Publié: (2026)

Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models
par: Wu, Haotian, et autres
Publié: (2025)

Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering
par: Zhu, Jiajun, et autres
Publié: (2025)

Knowledge Graph Large Language Model (KG-LLM) for Link Prediction
par: Shu, Dong, et autres
Publié: (2024)

LLM-Guided Knowledge Distillation for Temporal Knowledge Graph Reasoning
par: Xing, Wang, et autres
Publié: (2026)