Image de couverture de livre

Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sorensen, Taylor, Newman, Benjamin, Moore, Jared, Park, Chan, Fisher, Jillian, Mireshghallah, Niloofar, Jiang, Liwei, Choi, Yejin
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

Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models
par: Ravichander, Abhilasha, et autres
Publié: (2025)

A Roadmap to Pluralistic Alignment
par: Sorensen, Taylor, et autres
Publié: (2024)

Can Language Models Reason about Individualistic Human Values and Preferences?
par: Jiang, Liwei, et autres
Publié: (2024)

Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration
par: Feng, Shangbin, et autres
Publié: (2024)

Opt-ICL at LeWiDi-2025: Maximizing In-Context Signal from Rater Examples via Meta-Learning
par: Sorensen, Taylor, et autres
Publié: (2025)

Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing
par: Jung, Jaehun, et autres
Publié: (2023)

Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild
par: Mireshghallah, Niloofar, et autres
Publié: (2024)

JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
par: Fisher, Jillian, et autres
Publié: (2024)

The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
par: Hallinan, Skyler, et autres
Publié: (2025)

Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection
par: Naseh, Ali, et autres
Publié: (2025)

Position: Privacy Is Not Just Memorization!
par: Mireshghallah, Niloofar, et autres
Publié: (2025)

AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
par: Lu, Ximing, et autres
Publié: (2024)

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
par: Jiang, Liwei, et autres
Publié: (2024)

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
par: Mireshghallah, Niloofar, et autres
Publié: (2023)

FDARxBench: Benchmarking Regulatory and Clinical Reasoning on FDA Generic Drug Assessment
par: Xiong, Betty, et autres
Publié: (2026)

Reinforcement Learning Improves Traversal of Hierarchical Knowledge in LLMs
par: Zhang, Renfei, et autres
Publié: (2025)

Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
par: Kassem, Aly M., et autres
Publié: (2024)

SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
par: Li, Jing-Jing, et autres
Publié: (2024)

StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements
par: Fisher, Jillian, et autres
Publié: (2024)

DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life
par: Chiu, Yu Ying, et autres
Publié: (2024)

Smaller Language Models are Better Black-box Machine-Generated Text Detectors
par: Mireshghallah, Niloofar, et autres
Publié: (2023)

Do Membership Inference Attacks Work on Large Language Models?
par: Duan, Michael, et autres
Publié: (2024)

CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation
par: Chen, Tong, et autres
Publié: (2024)

EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences
par: Ghate, Kshitish, et autres
Publié: (2025)

Differentially Private Learning Needs Better Model Initialization and Self-Distillation
par: Ngong, Ivoline C., et autres
Publié: (2024)

A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage
par: Xin, Rui, et autres
Publié: (2025)

Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models
par: Liu, Xinyue, et autres
Publié: (2026)

What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations
par: Rao, Kavel, et autres
Publié: (2023)

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
par: Borkar, Jaydeep, et autres
Publié: (2025)

CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting
par: Li, Huihan, et autres
Publié: (2024)

Bob's Confetti: Phonetic Memorization Attacks in Music and Video Generation
par: Roh, Jaechul, et autres
Publié: (2025)

Developing Story: Case Studies of Generative AI's Use in Journalism
par: Brigham, Natalie Grace, et autres
Publié: (2024)

Boundary-targeted Membership Inference Attacks on Safety Classifiers
par: Hughes, Anthony, et autres
Publié: (2026)

WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries
par: Zhao, Wenting, et autres
Publié: (2024)

Political Neutrality in AI Is Impossible- But Here Is How to Approximate It
par: Fisher, Jillian, et autres
Publié: (2025)

SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs
par: Gu, Yuling, et autres
Publié: (2024)

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties
par: Sorensen, Taylor, et autres
Publié: (2023)

The Coverage Principle: How Pre-Training Enables Post-Training
par: Chen, Fan, et autres
Publié: (2025)

Tuning Language Models by Proxy
par: Liu, Alisa, et autres
Publié: (2024)

Intuitions of Compromise: Utilitarianism vs. Contractualism
par: Moore, Jared, et autres
Publié: (2024)