Where does output diversity collapse in post-training?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Karouzos, Constantinos, Tan, Xingwei, Aletras, Nikolaos
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
by: Karouzos, Constantinos, et al.
Published: (2026)

Incorporating Attribution Importance for Improving Faithfulness Metrics
by: Zhao, Zhixue, et al.
Published: (2023)

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?
by: Lewis-Lim, Samuel, et al.
Published: (2025)

Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models
by: Villegas, Danae Sánchez, et al.
Published: (2026)

Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models
by: Tan, Xingwei, et al.
Published: (2026)

Self-Improving Pretraining: using post-trained models to pretrain better models
by: Tan, Ellen Xiaoqing, et al.
Published: (2026)

Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models
by: Zhao, Zhixue, et al.
Published: (2024)

Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs
by: Gan, Xingwei, et al.
Published: (2026)

Bridging the Gap: From Ad-hoc to Proactive Search in Conversations
by: Meng, Chuan, et al.
Published: (2025)

How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?
by: Yamaguchi, Atsuki, et al.
Published: (2024)

An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference
by: Yamaguchi, Atsuki, et al.
Published: (2024)

Where Do Reasoning Models Refuse?
by: Yamaguchi, Kureha, et al.
Published: (2025)

Why mask diffusion does not work
by: Sun, Haocheng, et al.
Published: (2025)

Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance
by: Alajrami, Ahmed, et al.
Published: (2025)

Fantastic Bugs and Where to Find Them in AI Benchmarks
by: Truong, Sang, et al.
Published: (2025)

Decoupling the "What" and "Where" With Polar Coordinate Positional Embeddings
by: Gopalakrishnan, Anand, et al.
Published: (2025)

Efficient Prompt Tuning by Multi-Space Projection and Prompt Fusion
by: Lan, Pengxiang, et al.
Published: (2024)

Where Norms and References Collide: Evaluating LLMs on Normative Reasoning
by: Abrams, Mitchell, et al.
Published: (2026)

Where Pretraining writes and Alignment reads: the asymmetry of Transformer weight space
by: Ruscio, Valeria, et al.
Published: (2026)

From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
by: Tan, Yuqiao, et al.
Published: (2026)

Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models
by: Beniwal, Himanshu, et al.
Published: (2026)

Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process
by: Zhang, Zhenyu, et al.
Published: (2025)

Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization
by: Chrysostomou, George, et al.
Published: (2023)

Adapting Chat Language Models Using Only Target Unlabeled Language Data
by: Yamaguchi, Atsuki, et al.
Published: (2024)

Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
by: Yamaguchi, Atsuki, et al.
Published: (2025)

Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR
by: Kim, Soeun, et al.
Published: (2026)

Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
by: Xue, Huiyin, et al.
Published: (2025)

Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing
by: Li, Zhe, et al.
Published: (2025)

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
by: Wang, Ziyan, et al.
Published: (2025)

Prioritized Replay for RL Post-training
by: Fatemi, Mehdi
Published: (2026)

FECT: Factuality Evaluation of Interpretive AI-Generated Claims in Contact Center Conversation Transcripts
by: Shin, Hagyeong, et al.
Published: (2025)

Automatic Pair Construction for Contrastive Post-training
by: Xu, Canwen, et al.
Published: (2023)

Aviary: training language agents on challenging scientific tasks
by: Narayanan, Siddharth, et al.
Published: (2024)

Post-training for Efficient Communication via Convention Formation
by: Hua, Yilun, et al.
Published: (2025)

Investigating Data Contamination for Pre-training Language Models
by: Jiang, Minhao, et al.
Published: (2024)

Aligning Pre-trained Models for Spoken Language Translation
by: Sedláček, Šimon, et al.
Published: (2024)

Efficient Post-training Quantization with FP8 Formats
by: Shen, Haihao, et al.
Published: (2023)

Sequence-to-Sequence Spanish Pre-trained Language Models
by: Araujo, Vladimir, et al.
Published: (2023)

We Need to Talk About Classification Evaluation Metrics in NLP
by: Vickers, Peter, et al.
Published: (2024)

Negation Neglect: When models fail to learn negations in training
by: Mayne, Harry, et al.
Published: (2026)