arXiv AI
LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 28
How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift
arXiv:2607. 22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks.
Hugging Face Trending Papers
Jun 17
The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
arXiv AI
Sep 15
Ventriloquist LLMs: Linear Alignment of Late-Stage Representations
arXiv:2603.18908v5 Announce Type: replace Abstract: Independently trained language models often learn compatible late-stage representations, despite differences in training objectives, architectures,...
arXiv AI
Aug 24
RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
arXiv:2605.01913v2 Announce Type: replace-cross Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vul...
arXiv Computation and Language
Sep 4
Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations
The paper introduces IndicReStruct, a benchmark dataset comprising two variants—GSM8K-Reordered and GSM8K-Voice—derived from GSM8K to test multilingual LLMs on Hindi and Malayalam. It evaluates six state‑of‑the‑art LLMs under constrained constituent reordering and active‑passive voice transformation, finding consistent and significant drops in mathematical reasoning performance. Qualitative error analysis and residual‑stream activation patching reveal that failures often stem from disrupted entity‑quantity alignment, with intermediate transformer layers playing a key role in restoring reasoning.
arXiv AI
Aug 25
An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
The paper investigates how preference tuning—optimizing language models with explicit preference signals—behaves when applied to new domains. It systematically compares five alignment objectives and several adaptation strategies, such as target‑domain supervised fine‑tuning and pseudo‑labeling, across summarization, question‑answering helpfulness, and safety tasks. Results show that while pseudo‑labeling reduces domain‑shift degradation, it also causes mode collapse, highlighting a trade‑off between generalization and diversity.