Cover Image

Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Zhaowei, Liu, Xiaohan, Zhu, Xuekai, Huang, Junchao, Zhang, Ceyao, Feng, Zhiyuan, Yang, Yaodong, Yi, Xiaoyuan, Xie, Xing
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language Machine Learning I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
by: Zhang, Zhaowei, et al.
Published: (2025)

How Many Parameters Does Your Task Really Need? Task Specific Pruning with LLM-Sieve
by: Reda, Waleed, et al.
Published: (2025)

New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVR
by: Wang, Zhilin, et al.
Published: (2026)

JURY-RL: Votes Propose, Proofs Dispose for Label-Free RLVR
by: Chen, Xinjie, et al.
Published: (2026)

PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives
by: Zhang, Zhaowei, et al.
Published: (2025)

PhysNote: Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model
by: Zhang, Sinin, et al.
Published: (2026)

From Noise to Diversity: Random Embedding Injection in LLM Reasoning
by: Kim, Heejun, et al.
Published: (2026)

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

A Framework for Testing and Adapting REST APIs as LLM Tools
by: Bandlamudi, Jayachandu, et al.
Published: (2025)

Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games
by: Wu, Dekun, et al.
Published: (2023)

Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values
by: Dickerson, John P., et al.
Published: (2025)

Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning
by: Zhang, Li, et al.
Published: (2025)

Not All Thoughts Need HBM: Semantics-Aware Memory Hierarchy for LLM Reasoning
by: Yuan, Aojie, et al.
Published: (2026)

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

Steer-MoE: Efficient Audio-Language Alignment with a Mixture-of-Experts Steering Module
by: Feng, Ruitao, et al.
Published: (2025)

Have Multimodal Large Language Models (MLLMs) Really Learned to Tell the Time on Analog Clocks?
by: Fu, Tairan, et al.
Published: (2025)

Adapting Methods for Domain-Specific Japanese Small LMs: Scale, Architecture, and Quantization
by: Yasuno, Takato
Published: (2026)

D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree
by: Lei, Xiang, et al.
Published: (2025)

Multi-Hierarchical Feature Detection for Large Language Model Generated Text
by: Zhang, Luyan, et al.
Published: (2025)

When Does Data Augmentation Help? Evaluating LLM and Back-Translation Methods for Hausa and Fongbe NLP
by: Adjovi, Mahounan Pericles, et al.
Published: (2026)

AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention
by: Hu, Yuxuan, et al.
Published: (2026)

How Does Unfaithful Reasoning Emerge from Autoregressive Training? A Study of Synthetic Experiments
by: Wang, Fuxin, et al.
Published: (2026)

HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
by: He, Yongquan, et al.
Published: (2024)

Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning
by: Tong, Jingqi, et al.
Published: (2025)

Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuning
by: Bi, Jing, et al.
Published: (2024)

sudoLLM: On Multi-role Alignment of Language Models
by: Saha, Soumadeep, et al.
Published: (2025)

Adapting Multilingual Models to Code-Mixed Tasks via Model Merging
by: Kodali, Prashant, et al.
Published: (2025)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
by: Fadli, Samih
Published: (2025)

OpenAI Cribbed Our Tax Example, But Can GPT-4 Really Do Tax?
by: Blair-Stanek, Andrew, et al.
Published: (2023)

Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning
by: Ye, Hua, et al.
Published: (2025)

Towards Fundamental Language Models: Does Linguistic Competence Scale with Model Size?
by: Collado-Montañez, Jaime, et al.
Published: (2025)

Toward Architecture-Aware Evaluation Metrics for LLM Agents
by: Souza, Débora, et al.
Published: (2026)

A Statistical Framework for Alignment with Biased AI Feedback
by: Xia, Xintao, et al.
Published: (2026)

ReTreVal: Reasoning Tree with Validation -- A Hybrid Framework for Enhanced LLM Multi-Step Reasoning
by: HS, Abhishek, et al.
Published: (2026)

Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs
by: Eisenstadt, Roy, et al.
Published: (2025)

Cross-lingual Transfer in Programming Languages: An Extensive Empirical Study
by: Baltaji, Razan, et al.
Published: (2023)

HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns
by: Wang, Xintao, et al.
Published: (2026)

Induce, Align, Predict: Zero-Shot Stance Detection via Cognitive Inductive Reasoning
by: Zhang, Bowen, et al.
Published: (2025)

Large Language Models as Oracles for Ontology Alignment
by: Lushnei, Sviatoslav, et al.
Published: (2025)

Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models
by: Lu, Haolang, et al.
Published: (2025)