Newest papers

Unintended Side Effects of Value Training in LLMs

Siddhesh Pawar, Chen Cecilia Liu, Anna Korhonen, Isabelle Augenstein · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29922 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

كما يتم توزيع LLM في سياقات معيّنة من القيمة بشكل متزايد، فإن التوازن بينها مع القيم الإنسانية أصبحت هدفًا بعد التدريب في NLP، ويهدف إلى تزويد القيم الإضافية وممارسة السلوكيات النموذجية. ومع ذلك، لا تزال التقييمات الحالية ضعيفة. لأن القيم متصلة، فمن غير الواضح كيف تغيّر التقييم الجانبي لمقاصد معيّنة القدرات والممارسات غير ذات الصلة. في هذا العمل، نحن نكفّر أربعة LLMات معيّنة من التقييمات على أبعاد القيمة الفردية في Hofstede وتقييمها على كل من نقل القيمة المزدوجة والتصرفات الأوسع. ونحن نجد أن التدريب المحدّ

Machine translation (Meta M2M100); the English original follows.

Abstract

As LLMs are increasingly deployed in value-sensitive contexts, aligning them with human values has emerged as a post-training objective in NLP, aimed at instilling additional values and guiding model behaviour. However, current evaluations remain narrow. Because values are interconnected, it is unclear how fine-tuning for specific values alters unrelated capabilities and behaviours. In this work, we adapt four instruction-tuned LLMs across individual Hofstede's value dimensions and evaluate them on both cross-value transfer and broader behaviours. We find that value-specific training produces unintended side effects on untrained values, risk preferences, social cognition, and safety traits. Consequently, we suggest that value alignment after post-training should incorporate broader behavioral evaluations, and we highlight the need to investigate where additional value training might best fit into the pipeline.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Unintended consequences, Value (mathematics), Training (meteorology), Psychology, Economics, Public economics

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29922, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange