Copertina

MentorCollab: Selective Large-to-Small Inference-Time Guidance for Efficient Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Haojin, Wang, Yike, Feng, Shangbin, Hajishirzi, Hannaneh, Tsvetkov, Yulia
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ScienceMeter: Tracking Scientific Knowledge Updates in Language Models
di: Wang, Yike, et al.
Pubblicazione: (2025)

Small Reward Models via Backward Inference
di: Wang, Yike, et al.
Pubblicazione: (2026)

Data Swarms: Optimizable Generation of Synthetic Evaluation Data
di: Feng, Shangbin, et al.
Pubblicazione: (2025)

Resolving Knowledge Conflicts in Large Language Models
di: Wang, Yike, et al.
Pubblicazione: (2023)

Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration
di: Feng, Shangbin, et al.
Pubblicazione: (2024)

Don't Throw Away Your Pretrained Model
di: Feng, Shangbin, et al.
Pubblicazione: (2025)

ComPO: Community Preferences for Language Model Personalization
di: Kumar, Sachin, et al.
Pubblicazione: (2024)

Do Membership Inference Attacks Work on Large Language Models?
di: Duan, Michael, et al.
Pubblicazione: (2024)

Fine-grained Hallucination Detection and Editing for Language Models
di: Mishra, Abhika, et al.
Pubblicazione: (2024)

The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems
di: Feng, Shangbin, et al.
Pubblicazione: (2026)

Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems
di: Yang, Ziyuan, et al.
Pubblicazione: (2026)

David helps Goliath: Inference-Time Collaboration Between Small Specialized and Large General Diffusion LMs
di: Han, Xiaochuang, et al.
Pubblicazione: (2023)

APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
di: Zhao, Bowen, et al.
Pubblicazione: (2024)

What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection
di: Feng, Shangbin, et al.
Pubblicazione: (2024)

Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models
di: Ding, Wenxuan, et al.
Pubblicazione: (2023)

SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat
di: Jiang, Yuru, et al.
Pubblicazione: (2025)

Can LLM Graph Reasoning Generalize beyond Pattern Memorization?
di: Zhang, Yizhuo, et al.
Pubblicazione: (2024)

Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
di: Yao, Jihan, et al.
Pubblicazione: (2024)

DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection
di: Wan, Herun, et al.
Pubblicazione: (2024)

GuessBench: Sensemaking Multimodal Creativity in the Wild
di: Zhu, Zifeng, et al.
Pubblicazione: (2025)

Know Your Limits: A Survey of Abstention in Large Language Models
di: Wen, Bingbing, et al.
Pubblicazione: (2024)

KGQuiz: Evaluating the Generalization of Encoded Knowledge in Large Language Models
di: Bai, Yuyang, et al.
Pubblicazione: (2023)

MatFormer: Nested Transformer for Elastic Inference
di: Devvrit, et al.
Pubblicazione: (2023)

FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text
di: Boonsanong, Varich, et al.
Pubblicazione: (2025)

Can Language Models Solve Graph Problems in Natural Language?
di: Wang, Heng, et al.
Pubblicazione: (2023)

Teaching LLMs to Abstain across Languages via Multilingual Feedback
di: Feng, Shangbin, et al.
Pubblicazione: (2024)

BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
di: Cao, Qingqing, et al.
Pubblicazione: (2023)

Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models
di: Feng, Shangbin, et al.
Pubblicazione: (2023)

Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment
di: Zhang, Yizhuo, et al.
Pubblicazione: (2025)

Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time
di: Yang, Wang, et al.
Pubblicazione: (2025)

MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning
di: Li, Shuyue Stella, et al.
Pubblicazione: (2024)

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
di: Feng, Shangbin, et al.
Pubblicazione: (2025)

Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning
di: Kim, Joongwon, et al.
Pubblicazione: (2024)

Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection
di: Ahuja, Kabir, et al.
Pubblicazione: (2025)

HREF: Human Response-Guided Evaluation of Instruction Following in Language Models
di: Lyu, Xinxi, et al.
Pubblicazione: (2024)

ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context
di: Kim, Joongwon, et al.
Pubblicazione: (2025)

Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration
di: Feng, Shangbin, et al.
Pubblicazione: (2024)

Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks
di: Wang, Yichen, et al.
Pubblicazione: (2024)

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
di: Feng, Shangbin, et al.
Pubblicazione: (2024)

EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees
di: Zeng, Zhiyuan, et al.
Pubblicazione: (2025)