Image de couverture de livre

How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Asawa, Parth, Zhu, Alan, O'Neill, Abigail, Zaharia, Matei, Dimakis, Alexandros G., Gonzalez, Joseph E.
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SIEVE: Sample-Efficient Parametric Learning from Natural Language
par: Asawa, Parth, et autres
Publié: (2026)

BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation
par: Zhu, Alan, et autres
Publié: (2025)

Semantic Operators: A Declarative Model for Rich, AI-based Data Processing
par: Patel, Liana, et autres
Publié: (2024)

Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest
par: O'Neill, Abigail, et autres
Publié: (2026)

Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs
par: Huang, Yue, et autres
Publié: (2026)

Physio: An LLM-Based Physiotherapy Advisor
par: Almeida, Rúben, et autres
Publié: (2024)

When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models
par: Sanyal, Sunny, et autres
Publié: (2024)

LLMIA: An Out-of-the-Box Index Advisor via In-Context Learning with LLMs
par: Zhao, Xinxin, et autres
Publié: (2025)

Are Generative AI Agents Effective Personalized Financial Advisors?
par: Takayanagi, Takehiro, et autres
Publié: (2025)

AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence
par: Kim, Minbeom, et autres
Publié: (2024)

Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models
par: Wang, Fei, et autres
Publié: (2024)

Paired Completion: Flexible Quantification of Issue-framing at Scale with LLMs
par: Angus, Simon D, et autres
Publié: (2024)

The Media Specialist: How To Become Your District's Advisor on the No Child Left Behind Act.
par: Smith, Merna
Publié: (2002)

The Readers' Advisor's Companion.
par: Shearer, Kenneth D., Ed., et autres
Publié: (2001)

The Portable Dissertation Advisor.
par: Bryant, Miles T.
Publié: (2003)

Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection
par: Hu, Beizhe, et autres
Publié: (2023)

Consulting Multiple Advisors: When It Hurts and When It Does Not Hurt the Advisor–Advisee Relationship?
par: Mauricio Palmeira, et autres
Publié: (2024)

RAFT: Adapting Language Model to Domain Specific RAG
par: Zhang, Tianjun, et autres
Publié: (2024)

Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines
par: Arabzadeh, Negar, et autres
Publié: (2026)

Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models
par: O'Neill, Charles, et autres
Publié: (2024)

TripAdvisor Hotel Dataset
par: Miñana Navarro, Ana, et autres
Publié: (2026)

Imputing Proxy Advisor Recommendations
par: Jonathon Zytnick
Publié: (2025)

Student to Advisor: The Power of Influence
par: Stephanie McCoy
Publié: (2024)

Discovering Elementary Discourse Units in Textual Data Using Canonical Correlation Analysis
par: Mehndiratta, Akanksha, et autres
Publié: (2024)

A Multi-view Discourse Framework for Integrating Semantic and Syntactic Features in Dialog Agents
par: Mehndiratta, Akanksha, et autres
Publié: (2025)

Enhancing Dialogue Systems with Discourse-Level Understanding Using Deep Canonical Correlation Analysis
par: Mehndiratta, Akanksha, et autres
Publié: (2025)

RAG over Thinking Traces Can Improve Reasoning Tasks
par: Arabzadeh, Negar, et autres
Publié: (2026)

DS SERVE: A Framework for Efficient and Scalable Neural Retrieval
par: Liu, Jinjian, et autres
Publié: (2025)

Choose Your Agent: Tradeoffs in Adopting AI Advisors, Coaches, and Delegates in Multi-Party Negotiation
par: Zhu, Kehang, et autres
Publié: (2026)

A Database by Any Other Name: Instructor Language Preferences for Library Resources
par: O'Neill, Brittany, et autres
Publié: (2023)

ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems
par: Saad-Falcon, Jon, et autres
Publié: (2023)

The Effect of Advisors' Incentives on Clients' Investments
par: DIEGO BATTISTON, et autres
Publié: (2026)

Long Context RAG Performance of Large Language Models
par: Leng, Quinn, et autres
Publié: (2024)

Syntriever: How to Train Your Retriever with Synthetic Data from LLMs
par: Kim, Minsang, et autres
Publié: (2025)

The Power of Board Games for Multidomain Learning in Young Children
par: O'Neill, Daniela K., et autres
Publié: (2022)

LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
par: Kolasani, Sai, et autres
Publié: (2025)

The Dissertation Literature Review: How Faculty Advisors Prepare Their Doctoral Candidates.
par: Zaporozhetz, Laurene Elizabeth
Publié: (1987)

Multimodal QUD: Inquisitive Questions from Scientific Figures
par: Wu, Yating, et autres
Publié: (2026)

Which questions should I answer? Salience Prediction of Inquisitive Questions
par: Wu, Yating, et autres
Publié: (2024)

Self-supervised Speech Models for Word-Level Stuttered Speech Detection
par: Shih, Yi-Jen, et autres
Publié: (2024)