Copertina

The Quantization Trap: Breaking Linear Scaling Laws in Multi-Hop Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Han, Henry, Liu, Xiyang, Wang, Xiaodong, Han, Fei, Li, Xiaodong
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
di: Sun, Jiashuo, et al.
Pubblicazione: (2026)

P$^2$ Law: Scaling Law for Post-Training After Model Pruning
di: Chen, Xiaodong, et al.
Pubblicazione: (2024)

Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning
di: Xu, Ke, et al.
Pubblicazione: (2026)

Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques
di: Li, Chen, et al.
Pubblicazione: (2024)

When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning
di: Fang, Sitong, et al.
Pubblicazione: (2025)

PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering
di: Li, Xingyu, et al.
Pubblicazione: (2026)

ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA
di: Zhao, Xinjie, et al.
Pubblicazione: (2025)

ReasonAgain: Using Extractable Symbolic Programs to Evaluate Mathematical Reasoning
di: Yu, Xiaodong, et al.
Pubblicazione: (2024)

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
di: Wang, Shenzhi, et al.
Pubblicazione: (2026)

DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entries
di: Liu, Xiaodong
Pubblicazione: (2024)

Breaking the Hourglass Phenomenon of Residual Quantization: Enhancing the Upper Bound of Generative Retrieval
di: Kuai, Zhirui, et al.
Pubblicazione: (2024)

Reasoning Court: Combining Reasoning, Action, and Judgment for Multi-Hop Reasoning
di: Wu, Jingtian, et al.
Pubblicazione: (2025)

Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs
di: Fu, Yao, et al.
Pubblicazione: (2025)

Examining Two Hop Reasoning Through Information Content Scaling
di: Johnston, David, et al.
Pubblicazione: (2025)

Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis
di: Yadav, Anushka, et al.
Pubblicazione: (2025)

Multi-Hop Reasoning for Question Answering with Hyperbolic Representations
di: Welz, Simon, et al.
Pubblicazione: (2025)

KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning
di: Wang, Shuai, et al.
Pubblicazione: (2026)

DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
di: Wang, Changhao, et al.
Pubblicazione: (2025)

Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
di: Bu, Yunhan, et al.
Pubblicazione: (2026)

Layer-Order Inversion: Rethinking Latent Multi-Hop Reasoning in Large Language Models
di: Liu, Xukai, et al.
Pubblicazione: (2026)

From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs
di: Bian, Haonan, et al.
Pubblicazione: (2025)

M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark
di: Zhou, Yang, et al.
Pubblicazione: (2025)

Mixture Policy based Multi-Hop Reasoning over N-tuple Temporal Knowledge Graphs
di: Hou, Zhongni, et al.
Pubblicazione: (2025)

Beyond Accuracy: An Empirical Study on Unit Testing in Open-source Deep Learning Projects
di: Wang, Han, et al.
Pubblicazione: (2024)

Tequila: Trapping-free Ternary Quantization for Large Language Models
di: Huang, Hong, et al.
Pubblicazione: (2025)

TempoGPT: Enhancing Time Series Reasoning via Quantizing Embedding
di: Zhang, Haochuan, et al.
Pubblicazione: (2025)

Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering
di: Kim, Ik-hwan, et al.
Pubblicazione: (2026)

A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA
di: Wan, Kaiyang, et al.
Pubblicazione: (2025)

Scaling Trends for Multi-Hop Contextual Reasoning in Mid-Scale Language Models
di: Steele, Brady, et al.
Pubblicazione: (2026)

RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
di: Yang, Ruiyi, et al.
Pubblicazione: (2025)

Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning
di: Wu, Xiaojun, et al.
Pubblicazione: (2025)

Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs
di: Thompson, Travis, et al.
Pubblicazione: (2025)

A Law Reasoning Benchmark for LLM with Tree-Organized Structures including Factum Probandum, Evidence and Experiences
di: Shen, Jiaxin, et al.
Pubblicazione: (2025)

OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
di: Liu, Yu, et al.
Pubblicazione: (2025)

Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models
di: Zhou, Chenxi, et al.
Pubblicazione: (2025)

Breaking the Blocks: Continuous Low-Rank Decomposed Scaling for Unified LLM Quantization and Adaptation
di: Tang, Pingzhi, et al.
Pubblicazione: (2026)

LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation
di: Liu, Yijun, et al.
Pubblicazione: (2024)

Scaling Laws for Precision in High-Dimensional Linear Regression
di: Zhang, Dechen, et al.
Pubblicazione: (2026)

Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models
di: Liu, Ruikang, et al.
Pubblicazione: (2025)

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks
di: Yu, Xiaodong, et al.
Pubblicazione: (2023)