Copertina

Understanding and Patching Compositional Reasoning in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Zhaoyi, Jiang, Gangwei, Xie, Hong, Song, Linqi, Lian, Defu, Wei, Ying
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
di: Li, Zhaoyi, et al.
Pubblicazione: (2026)

Learning to Substitute Components for Compositional Generalization
di: Li, Zhaoyi, et al.
Pubblicazione: (2025)

On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning
di: Li, Zhaoyi, et al.
Pubblicazione: (2026)

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
di: Zhong, Tianqi, et al.
Pubblicazione: (2024)

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing
di: Wang, Weichuan, et al.
Pubblicazione: (2024)

Mitigate Negative Transfer with Similarity Heuristic Lifelong Prompt Tuning
di: Wu, Chenyuan, et al.
Pubblicazione: (2024)

Refine Large Language Model Fine-tuning via Instruction Vector
di: Jiang, Gangwei, et al.
Pubblicazione: (2024)

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning
di: Jiang, Gangwei, et al.
Pubblicazione: (2025)

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning
di: Jiang, Gangwei, et al.
Pubblicazione: (2025)

HumanLLM: Towards Personalized Understanding and Simulation of Human Nature
di: Lei, Yuxuan, et al.
Pubblicazione: (2026)

LLM Cache Bandit Revisited: Addressing Query Heterogeneity for Cost-Effective LLM Inference
di: Yang, Hantao, et al.
Pubblicazione: (2025)

Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval
di: Lan, Junwei, et al.
Pubblicazione: (2025)

Benchmarking and Understanding Compositional Relational Reasoning of LLMs
di: Ni, Ruikang, et al.
Pubblicazione: (2024)

GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability
di: Luo, Zihan, et al.
Pubblicazione: (2024)

ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval
di: Chen, Jianlyu, et al.
Pubblicazione: (2025)

Advancing and Benchmarking Personalized Tool Invocation for LLMs
di: Huang, Xu, et al.
Pubblicazione: (2025)

Bi-Chainer: Automated Large Language Models Reasoning with Bidirectional Chaining
di: Liu, Shuqi, et al.
Pubblicazione: (2024)

O1 Embedder: Let Retrievers Think Before Action
di: Yan, Ruiran, et al.
Pubblicazione: (2025)

IE as Cache: Information Extraction Enhanced Agentic Reasoning
di: Lv, Hang, et al.
Pubblicazione: (2026)

DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
di: Lin, Haokun, et al.
Pubblicazione: (2024)

Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation
di: Luo, Sichun, et al.
Pubblicazione: (2025)

Invariant Representation via Decoupling Style and Spurious Features from Images
di: Li, Ruimeng, et al.
Pubblicazione: (2023)

Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models
di: Liu, Shuqi, et al.
Pubblicazione: (2025)

Emotion-o1: Adaptive Long Reasoning for Emotion Understanding in LLMs
di: Song, Changhao, et al.
Pubblicazione: (2025)

SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation
di: Lv, Hang, et al.
Pubblicazione: (2026)

Memorization or Reasoning? Exploring the Idiom Understanding of LLMs
di: Kim, Jisu, et al.
Pubblicazione: (2025)

LLM-BABYBENCH: Understanding and Evaluating Grounded Planning and Reasoning in LLMs
di: Choukrani, Omar, et al.
Pubblicazione: (2025)

Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval
di: Liu, Zheng, et al.
Pubblicazione: (2023)

Reinforced Information Retrieval
di: Li, Chaofan, et al.
Pubblicazione: (2025)

Understanding Privacy Risks of Embeddings Induced by Large Language Models
di: Zhu, Zhihao, et al.
Pubblicazione: (2024)

\texttt{ReMind}: Understanding Deductive Code Reasoning in LLMs
di: Gao, Jun, et al.
Pubblicazione: (2025)

Quantum-Audit: Evaluating the Reasoning Limits of LLMs on Quantum Computing
di: Afane, Mohamed, et al.
Pubblicazione: (2026)

Reasoning about Affordances: Causal and Compositional Reasoning in LLMs
di: Gjerde, Magnus F., et al.
Pubblicazione: (2025)

Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective
di: Wu, Chenwang, et al.
Pubblicazione: (2025)

Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement
di: Wu, Chenwang, et al.
Pubblicazione: (2026)

When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities
di: Chen, Jin, et al.
Pubblicazione: (2023)

Matryoshka Re-Ranker: A Flexible Re-Ranking Architecture With Configurable Depth and Width
di: Liu, Zheng, et al.
Pubblicazione: (2025)

Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
di: Liang, Xiao, et al.
Pubblicazione: (2026)

DiffETM: Diffusion Process Enhanced Embedded Topic Model
di: Shao, Wei, et al.
Pubblicazione: (2025)

Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations
di: Sun, Jiaxing, et al.
Pubblicazione: (2024)