Image de couverture de livre

How Do LLMs Perform Two-Hop Reasoning in Context?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Guo, Tianyu, Zhu, Hanlin, Zhang, Ruiqi, Jiao, Jiantao, Mei, Song, Jordan, Michael I., Russell, Stuart
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
par: Huang, Yixiao, et autres
Publié: (2025)

GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments
par: Zhu, Hanlin, et autres
Publié: (2025)

Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
par: Zhu, Banghua, et autres
Publié: (2024)

IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis
par: Li, Hanyu, et autres
Publié: (2025)

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
par: Su, DiJia, et autres
Publié: (2025)

Lessons from Studying Two-Hop Latent Reasoning
par: Balesni, Mikita, et autres
Publié: (2024)

GSM-Infinite: How Do Your LLMs Behave over Infinitely Increasing Context Length and Reasoning Complexity?
par: Zhou, Yang, et autres
Publié: (2025)

From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs
par: Bian, Haonan, et autres
Publié: (2025)

Thinking LLMs: General Instruction Following with Thought Generation
par: Wu, Tianhao, et autres
Publié: (2024)

How Likely Do LLMs with CoT Mimic Human Reasoning?
par: Bao, Guangsheng, et autres
Publié: (2024)

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning
par: Chen, Haoyang, et autres
Publié: (2026)

How Do LLMs Use Their Depth?
par: Gupta, Akshat, et autres
Publié: (2025)

Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
par: Zhu, Hanlin, et autres
Publié: (2024)

Reasoning Court: Combining Reasoning, Action, and Judgment for Multi-Hop Reasoning
par: Wu, Jingtian, et autres
Publié: (2025)

Under the Shadow of Babel: How Language Shapes Reasoning in LLMs
par: Wang, Chenxi, et autres
Publié: (2025)

What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA
par: Chang, Zhiyuan, et autres
Publié: (2024)

Is Depth All You Need? An Exploration of Iterative Reasoning in LLMs
par: Wu, Zongqian, et autres
Publié: (2025)

Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis
par: Yadav, Anushka, et autres
Publié: (2025)

How Well Do LLMs Understand Tunisian Arabic?
par: Mahdi, Mohamed
Publié: (2025)

Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons
par: Zhu, Banghua, et autres
Publié: (2023)

Multi-Hop Reasoning for Question Answering with Hyperbolic Representations
par: Welz, Simon, et autres
Publié: (2025)

LLMs for Relational Reasoning: How Far are We?
par: Li, Zhiming, et autres
Publié: (2024)

How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
par: Cui, Yingqian, et autres
Publié: (2026)

Do LLMs Really Think Step-by-step In Implicit Reasoning?
par: Yu, Yijiong
Publié: (2024)

CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning
par: Cui, Hao, et autres
Publié: (2025)

Contextual Drag: How Errors in the Context Affect LLM Reasoning
par: Cheng, Yun, et autres
Publié: (2026)

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
par: Mei, Zhiting, et autres
Publié: (2025)

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
par: Wang, Shenzhi, et autres
Publié: (2026)

ToxiLab: How Well Do Open-Source LLMs Generate Synthetic Toxicity Data?
par: Hui, Zheng, et autres
Publié: (2024)

Avoiding Catastrophe in Online Learning by Asking for Help
par: Plaut, Benjamin, et autres
Publié: (2024)

How Reliable are LLMs for Reasoning on the Re-ranking task?
par: Islam, Nafis Tanveer, et autres
Publié: (2025)

KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning
par: Wang, Shuai, et autres
Publié: (2026)

BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack
par: Kuratov, Yuri, et autres
Publié: (2024)

RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
par: Yang, Ruiyi, et autres
Publié: (2025)

Do LLMs Exhibit Human-Like Reasoning? Evaluating Theory of Mind in LLMs for Open-Ended Responses
par: Amirizaniani, Maryam, et autres
Publié: (2024)

Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?
par: Bhambri, Siddhant, et autres
Publié: (2025)

What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices
par: Chen, Zhi, et autres
Publié: (2024)

CreDes: Causal Reasoning Enhancement and Dual-End Searching for Solving Long-Range Reasoning Problems using LLMs
par: Wang, Kangsheng, et autres
Publié: (2024)

A Tale of Two Structures: Do LLMs Capture the Fractal Complexity of Language?
par: Alabdulmohsin, Ibrahim, et autres
Publié: (2025)

Evaluating the Sensitivity of LLMs to Prior Context
par: Hankache, Robert, et autres
Publié: (2025)