Copertina

Do Large Language Models Latently Perform Multi-Hop Reasoning?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Sohee, Gribovskaya, Elena, Kassner, Nora, Geva, Mor, Riedel, Sebastian
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

Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?
di: Yang, Sohee, et al.
Pubblicazione: (2024)

How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?
di: Yang, Sohee, et al.
Pubblicazione: (2025)

Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries
di: Biran, Eden, et al.
Pubblicazione: (2024)

Estimating Knowledge in Large Language Models Without Generating a Single Token
di: Gottesman, Daniela, et al.
Pubblicazione: (2024)

Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?
di: Yona, Gal, et al.
Pubblicazione: (2024)

Detecting (Un)answerability in Large Language Models with Linear Directions
di: Lavi, Maor Juliet, et al.
Pubblicazione: (2025)

Performance Gap in Entity Knowledge Extraction Across Modalities in Vision Language Models
di: Cohen, Ido, et al.
Pubblicazione: (2024)

Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models
di: Yalon, Noam Steinmetz, et al.
Pubblicazione: (2026)

Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
di: Gur-Arieh, Yoav, et al.
Pubblicazione: (2025)

Inferring Functionality of Attention Heads from their Parameters
di: Elhelo, Amit, et al.
Pubblicazione: (2024)

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

Precise In-Parameter Concept Erasure in Large Language Models
di: Gur-Arieh, Yoav, et al.
Pubblicazione: (2025)

Latent Reasoning with Supervised Thinking States
di: Amos, Ido, et al.
Pubblicazione: (2026)

Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers
di: Yona, Gal, et al.
Pubblicazione: (2024)

Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models
di: Prato, Gabriele, et al.
Pubblicazione: (2025)

Preventing Rogue Agents Improves Multi-Agent Collaboration
di: Barbi, Ohav, et al.
Pubblicazione: (2025)

Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models
di: Yona, Itay, et al.
Pubblicazione: (2026)

From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty
di: Ivgi, Maor, et al.
Pubblicazione: (2024)

Constructing Interpretable Features from Compositional Neuron Groups
di: Shafran, Or, et al.
Pubblicazione: (2025)

Eliciting Textual Descriptions from Representations of Continuous Prompts
di: Ramati, Dana, et al.
Pubblicazione: (2024)

Hallucinations Undermine Trust; Metacognition is a Way Forward
di: Yona, Gal, et al.
Pubblicazione: (2026)

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
di: Yu, Zeping, et al.
Pubblicazione: (2025)

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
di: Katz, Shahar, et al.
Pubblicazione: (2024)

ActiShade: Activating Overshadowed Knowledge to Guide Multi-Hop Reasoning in Large Language Models
di: Ma, Huipeng, et al.
Pubblicazione: (2026)

From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
di: Shafran, Or, et al.
Pubblicazione: (2026)

Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge
di: Zhang, Haotong
Pubblicazione: (2024)

RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations
di: Huang, Jing, et al.
Pubblicazione: (2024)

Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts
di: Ahrac, Sagi, et al.
Pubblicazione: (2026)

Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
di: Gur-Arieh, Yoav, et al.
Pubblicazione: (2026)

Disentangling MLP Neuron Weights in Vocabulary Space
di: Avrahamy, Asaf, et al.
Pubblicazione: (2026)

How Do LLMs Perform Two-Hop Reasoning in Context?
di: Guo, Tianyu, et al.
Pubblicazione: (2025)

Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context
di: Yu, Sangwon, et al.
Pubblicazione: (2024)

Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study
di: Khodadad, Mohammad, et al.
Pubblicazione: (2025)

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
di: Gekhman, Zorik, et al.
Pubblicazione: (2026)

The Hidden Space of Transformer Language Adapters
di: Alabi, Jesujoba O., et al.
Pubblicazione: (2024)

Making Long-Context Language Models Better Multi-Hop Reasoners
di: Li, Yanyang, et al.
Pubblicazione: (2024)

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
di: Ghandeharioun, Asma, et al.
Pubblicazione: (2024)

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

Rethinking Selective Knowledge Distillation
di: Tavor, Almog, et al.
Pubblicazione: (2026)

Auto-Patching: Enhancing Multi-Hop Reasoning in Language Models
di: Jan, Aviv, et al.
Pubblicazione: (2025)