Cover Image

Enhancing Small LLM Alignment through Margin-Based Objective Modifications under Resource Constraints

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yao, Daren, Yuan, Jinsong, Chen, Ruike
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction
by: Wang, Daren, et al.
Published: (2026)

Think, But Don't Overthink: Reproducing Recursive Language Models
by: Wang, Daren
Published: (2026)

Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback
by: Kim, Kyuyoung, et al.
Published: (2024)

Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence Scoring
by: Chen, Shiting, et al.
Published: (2025)

SaRO: Enhancing LLM Safety through Reasoning-based Alignment
by: Mou, Yutao, et al.
Published: (2025)

Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments
by: Wang, Jiashuo, et al.
Published: (2025)

Improving LLM Safety Alignment with Dual-Objective Optimization
by: Zhao, Xuandong, et al.
Published: (2025)

The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives
by: Bou, Matthieu, et al.
Published: (2025)

Enhancing Cross-Lingual Transfer through Reversible Transliteration: A Huffman-Based Approach for Low-Resource Languages
by: Zhuang, Wenhao, et al.
Published: (2025)

Transferable Modeling Strategies for Low-Resource LLM Tasks: A Prompt and Alignment-Based Approach
by: Lyu, Shuangquan, et al.
Published: (2025)

Empirical Evidence for Alignment Faking in a Small LLM and Prompt-Based Mitigation Techniques
by: Koorndijk, Jeanice
Published: (2025)

StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models
by: Khan, Ishmam, et al.
Published: (2026)

Uncovering Cross-Objective Interference in Multi-Objective Alignment
by: Lu, Yining, et al.
Published: (2026)

Reward-free Alignment for Conflicting Objectives
by: Chen, Peter, et al.
Published: (2026)

Unlocking LLM Safeguards for Low-Resource Languages via Reasoning and Alignment with Minimal Training Data
by: Chen, Zhuowei, et al.
Published: (2025)

R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning
by: Zhao, Qingfei, et al.
Published: (2025)

Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis
by: Gisserot-Boukhlef, Hippolyte, et al.
Published: (2024)

Discovering Implicit Large Language Model Alignment Objectives
by: Chen, Edward, et al.
Published: (2026)

Capturing Symmetry and Antisymmetry in Language Models through Symmetry-Aware Training Objectives
by: Yuan, Zhangdie, et al.
Published: (2025)

OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
by: Lin, Liang, et al.
Published: (2025)

Leveraging Robust Optimization for LLM Alignment under Distribution Shifts
by: Zhu, Mingye, et al.
Published: (2025)

Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment
by: Cai, Wenrui, et al.
Published: (2025)

Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards
by: Zeng, Xia, et al.
Published: (2025)

Enhancing Speech Large Language Models through Reinforced Behavior Alignment
by: Liu, Yansong, et al.
Published: (2025)

MOA: Multi-Objective Alignment for Role-Playing Agents
by: Liao, Chonghua, et al.
Published: (2025)

Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations
by: Lai, Peng, et al.
Published: (2025)

Documents Are People and Words Are Items: A Psychometric Approach to Textual Data with Contextual Embeddings
by: Chen, Jinsong
Published: (2025)

Safe at the Margins: A General Approach to Safety Alignment in Low-Resource English Languages -- A Singlish Case Study
by: Lim, Isaac, et al.
Published: (2025)

RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation
by: Jiang, Pengcheng, et al.
Published: (2025)

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization
by: Wadhwa, Sahil, et al.
Published: (2024)

Length-Controlled Margin-Based Preference Optimization without Reference Model
by: Li, Gengxu, et al.
Published: (2025)

Fine-grained Analysis of Brain-LLM Alignment through Input Attribution
by: Proietti, Michela, et al.
Published: (2025)

UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment
by: Xie, Hongyan, et al.
Published: (2026)

Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment
by: Guo, Yiju, et al.
Published: (2024)

ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreaks
by: Kim, Hyunjun, et al.
Published: (2025)

Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts
by: Yin, Yueqin, et al.
Published: (2024)

Larger or Smaller Reward Margins to Select Preferences for Alignment?
by: Huang, Kexin, et al.
Published: (2025)

Token-Level Marginalization for Multi-Label LLM Classifiers
by: Praharaj, Anjaneya, et al.
Published: (2025)

AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment
by: Deng, Ruibo, et al.
Published: (2025)

Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series
by: Hu, Yuxiao, et al.
Published: (2025)