Image de couverture de livre

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Jiayi, Yu, Simon, Chong, Derek, Sicilia, Anthony, Tomz, Michael R., Manning, Christopher D., Shi, Weiyan
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

Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace
par: Yu, Simon, et autres
Publié: (2026)

Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors
par: Sicilia, Anthony, et autres
Publié: (2024)

Annotations Mitigate Post-Training Mode Collapse
par: Springer, Jacob Mitchell, et autres
Publié: (2026)

Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios
par: Hassan, Sabit, et autres
Publié: (2024)

ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation
par: Wu, Zhengxuan, et autres
Publié: (2023)

Measuring How (Not Just Whether) VLMs Build Common Ground
par: Imai, Saki, et autres
Publié: (2025)

Evaluating Theory of (an uncertain) Mind: Predicting the Uncertain Beliefs of Others in Conversation Forecasting
par: Sicilia, Anthony, et autres
Publié: (2024)

Train Yourself as an LLM: Exploring Effects of AI Literacy on Persuasion via Role-playing LLM Training
par: Fan, Qihui, et autres
Publié: (2026)

PolySkill: Learning Generalizable Skills Through Polymorphic Abstraction
par: Yu, Simon, et autres
Publié: (2025)

How do LLMs Compute Verbal Confidence
par: Kumaran, Dharshan, et autres
Publié: (2026)

Change My View? The Dynamics of Persuasion and Polarization in Online Discourse
par: Freeborn, David, et autres
Publié: (2026)

An Active Learning Framework for Inclusive Generation by Large Language Models
par: Hassan, Sabit, et autres
Publié: (2024)

Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
par: Yuan, Jiayi, et autres
Publié: (2025)

From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization
par: Zhou, Chenxi, et autres
Publié: (2026)

Humans and transformer LMs: Abstraction drives language learning
par: Jian, Jasper, et autres
Publié: (2026)

Mitigating Spurious Correlations in NLI via LLM-Synthesized Counterfactuals and Dynamic Balanced Sampling
par: Jaimes, Christopher Román
Publié: (2025)

Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
par: Maiti, Shalini, et autres
Publié: (2025)

Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinking
par: Ju, Feng, et autres
Publié: (2025)

Are LLM Decisions Faithful to Verbal Confidence?
par: Wang, Jiawei, et autres
Publié: (2026)

Escaping Mode Collapse in LLM Generation via Geometric Regulation
par: Du, Xin, et autres
Publié: (2026)

HumBEL: A Human-in-the-Loop Approach for Evaluating Demographic Factors of Language Models in Human-Machine Conversations
par: Sicilia, Anthony, et autres
Publié: (2023)

Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models
par: Zhang, Jiayi, et autres
Publié: (2025)

Accounting for Sycophancy in Language Model Uncertainty Estimation
par: Sicilia, Anthony, et autres
Publié: (2024)

Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling
par: Xiao, Tim Z., et autres
Publié: (2025)

Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator
par: Yuan, Peiwen, et autres
Publié: (2025)

Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model
par: Lou, Xinyue, et autres
Publié: (2025)

Improved Representation Steering for Language Models
par: Wu, Zhengxuan, et autres
Publié: (2025)

Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations
par: Ji, Ziwei, et autres
Publié: (2025)

BASIL: Bayesian Assessment of Sycophancy in LLMs
par: Atwell, Katherine, et autres
Publié: (2025)

SiLVERScore: Semantically-Aware Embeddings for Sign Language Generation Evaluation
par: Imai, Saki, et autres
Publié: (2025)

Osiris: A Lightweight Open-Source Hallucination Detection System
par: Shan, Alex, et autres
Publié: (2025)

Sneaking Syntax into Transformer Language Models with Tree Regularization
par: Nandi, Ananjan, et autres
Publié: (2024)

Detecting Mode Collapse in Language Models via Narration
par: Hamilton, Sil
Publié: (2024)

Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation
par: Zhou, Yuxuan, et autres
Publié: (2024)

Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarios
par: Chakraborty, Mohna, et autres
Publié: (2025)

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
par: Ding, Yiwen, et autres
Publié: (2024)

The Price of Format: Diversity Collapse in LLMs
par: Yun, Longfei, et autres
Publié: (2025)

How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
par: Zeng, Yi, et autres
Publié: (2024)

Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse
par: Zhang, Chi, et autres
Publié: (2026)

Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Models
par: Laitenberger, Alex, et autres
Publié: (2025)