AI ethics evidence index Search
Source-linked daily record
Evidence record 5933 · automatically gathered

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We attribute this gap to a mismatch between language-agnostic semantic understanding ability and language-dominant safety alignment biased toward high-resource languages. Consistent with this hypothesis, we empirically identify the semantic bottleneck in LLMs, an intermediate layer in which the geometry of model representa

Record details

Published: 13 April 2026
Source: arXiv
Category: Research
Topics: Bias & fairness · Safety & alignment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations

arXiv · 13 April 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions

arXiv · 13 April 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models

arXiv · 14 April 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment

arXiv · 14 April 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance

arXiv · 12 April 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

A Multi-Domain Red Teaming Framework for Safety, Robustness, and Fairness Evaluation of Medical Large Language Models

arXiv · 15 April 2026

How to cite this record

ethics.ai (13 April 2026), “LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety,” evidence record 5933, https://ethics.ai/record/5933 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.