Pith. sign in

REVIEW 4 cited by

Self-Pluralising Culture Alignment for Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.12971 v1 pith:PM76LUB3 submitted 2024-10-16 cs.CL

classification cs.CL
keywords culturesllmsalignmentcultureculturespapluralisticalignculture-aware
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As large language models (LLMs) become increasingly accessible in many countries, it is essential to align them to serve pluralistic human values across cultures. However, pluralistic culture alignment in LLMs remain an open problem. In this paper, we propose CultureSPA, a Self-Pluralising Culture Alignment framework that allows LLMs to simultaneously align to pluralistic cultures. The framework first generates questions on various culture topics, then yields LLM outputs in response to these generated questions under both culture-aware and culture-unaware settings. By comparing culture-aware/unaware outputs, we are able to detect and collect culture-related instances. These instances are employed to fine-tune LLMs to serve pluralistic cultures in either a culture-joint or culture-specific way. Extensive experiments demonstrate that CultureSPA significantly improves the alignment of LLMs to diverse cultures without compromising general abilities. And further improvements can be achieved if CultureSPA is combined with advanced prompt engineering techniques. Comparisons between culture-joint and culture-specific tuning strategies, along with variations in data quality and quantity, illustrate the robustness of our method. We also explore the mechanisms underlying CultureSPA and the relations between different cultures it reflects.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Roadmap to Impactful Pluralistic Alignment Research

    cs.AI 2026-07 accept novelty 6.0 of 10

    Pluralistic alignment research has produced no public evidence of adoption in deployed frontier models, so the field should focus on empirical justification, settled goals, and hill-climbable evaluations.

  2. LKValues: Aligning Large Language Models with Sri Lankan Societal Values

    cs.CL 2026-07 conditional novelty 6.0 of 10

    A survey-derived Sri Lankan value alignment suite (LKValues) with 150k instruction instances and a 1k benchmark improves Qwen-family LLMs' Sri Lankan value judgment in Sinhala and English.

  3. CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters

    cs.CL 2026-01 conditional novelty 6.0 of 10

    A demographic-conditioned mixture of LoRA experts improves LLM cultural alignment and reduces the tendency of dense models to produce generic, averaged responses.

  4. From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan

    cs.CL 2025-07 unverdicted novelty 4.0 of 10

    A 72GB Tibetan corpus enables continual pre-training of Qwen2.5-7B and a 50B-A10B MoE model, with new benchmarks showing outperformance over prior Tibetan models.

Pith tools