Imagen de Portada

Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Chalkidis, Ilias
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Llama meets EU: Investigating the European Political Spectrum through the Lens of LLMs
por: Chalkidis, Ilias, et al.
Publicado: (2024)

Investigating LLMs as Voting Assistants via Contextual Augmentation: A Case Study on the European Parliament Elections 2024
por: Chalkidis, Ilias
Publicado: (2024)

Identifying Fine-grained Forms of Populism in Political Discourse: A Case Study on Donald Trump's Presidential Campaigns
por: Chalkidis, Ilias, et al.
Publicado: (2025)

Efficient Document Embeddings via Self-Contrastive Bregman Divergence Learning
por: Saggau, Daniel, et al.
Publicado: (2023)

From Citations to Criticality: Predicting Legal Decision Influence in the Multilingual Swiss Jurisprudence
por: Stern, Ronja, et al.
Publicado: (2024)

Brainrot: Deskilling and Addiction are Overlooked AI Risks
por: Chalkidis, Ilias, et al.
Publicado: (2026)

Data-centric NLP Backdoor Defense from the Lens of Memorization
por: Wang, Zhenting, et al.
Publicado: (2024)

When Do Language Models Endorse Limitations on Human Rights Principles?
por: Samway, Keenan, et al.
Publicado: (2026)

MultiLegalPile: A 689GB Multilingual Legal Corpus
por: Niklaus, Joel, et al.
Publicado: (2023)

LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain
por: Niklaus, Joel, et al.
Publicado: (2023)

A Survey on Efficient Large Language Model Training: From Data-centric Perspectives
por: Luo, Junyu, et al.
Publicado: (2025)

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers
por: Langedijk, Anna, et al.
Publicado: (2023)

Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines
por: Song, Hwanjun
Publicado: (2026)

Survey-to-Behavior: Downstream Alignment of Human Values in LLMs via Survey Questions
por: Nie, Shangrui, et al.
Publicado: (2025)

LexMatcher: Dictionary-centric Data Collection for LLM-based Machine Translation
por: Yin, Yongjing, et al.
Publicado: (2024)

Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
por: Shu, Dong, et al.
Publicado: (2025)

LLM Bias Detection and Mitigation through the Lens of Desired Distributions
por: Shrestha, Ingroj, et al.
Publicado: (2025)

Transfer Q Star: Principled Decoding for LLM Alignment
por: Chakraborty, Souradip, et al.
Publicado: (2024)

Text-centric Alignment for Multi-Modality Learning
por: Tsai, Yun-Da, et al.
Publicado: (2024)

Rethinking LLM Memorization through the Lens of Adversarial Compression
por: Schwarzschild, Avi, et al.
Publicado: (2024)

Value Drifts: Tracing Value Alignment During LLM Post-Training
por: Bhatia, Mehar, et al.
Publicado: (2025)

From Hallucination to Structure Snowballing: The Alignment Tax of Constrained Decoding in LLM Reflection
por: Zhou, Hongxu
Publicado: (2026)

A Survey on Progress in LLM Alignment from the Perspective of Reward Design
por: Ji, Miaomiao, et al.
Publicado: (2025)

Error as a Lens: Probing LLM Reasoning through Synthetic Misconception Generation
por: Yang, Xinming, et al.
Publicado: (2026)

A Survey of Multimodal Large Language Model from A Data-centric Perspective
por: Bai, Tianyi, et al.
Publicado: (2024)

Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
por: Chakraborty, Souradip, et al.
Publicado: (2025)

SurveyLens: A Research Discipline-Aware Benchmark for Automatic Survey Generation
por: Guo, Beichen, et al.
Publicado: (2026)

KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge
por: Lee, Jiyoung, et al.
Publicado: (2024)

Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance
por: Hu, Wenbin, et al.
Publicado: (2025)

Political Bias in LLMs: Unaligned Moral Values in Agent-centric Simulations
por: Münker, Simon
Publicado: (2024)

LLMs with Industrial Lens: Deciphering the Challenges and Prospects -- A Survey
por: Urlana, Ashok, et al.
Publicado: (2024)

Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification
por: Wang, Jikai, et al.
Publicado: (2025)

Register Always Matters: Analysis of LLM Pretraining Data Through the Lens of Language Variation
por: Myntti, Amanda, et al.
Publicado: (2025)

Reframing Data Value for Large Language Models Through the Lens of Plausibility
por: Rammal, Mohamad Rida, et al.
Publicado: (2024)

Explanation Regularisation through the Lens of Attributions
por: Ferreira, Pedro, et al.
Publicado: (2024)

Ziya2: Data-centric Learning is All LLMs Need
por: Gan, Ruyi, et al.
Publicado: (2023)

Déjà Vu: Multilingual LLM Evaluation through the Lens of Machine Translation Evaluation
por: Kreutzer, Julia, et al.
Publicado: (2025)

Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys
por: Cao, Yong, et al.
Publicado: (2024)

Rendering Data Unlearnable by Exploiting LLM Alignment Mechanisms
por: Zhang, Ruihan, et al.
Publicado: (2026)

A Survey on Data Selection for LLM Instruction Tuning
por: Zhang, Bolin, et al.
Publicado: (2024)