← Back to all news
arXiv Machine Learning By Jessica Dierking, Itai Shapira, Niclas Boehmer

What Is Lost in Post-Training? Default Collapse and the Loss of In-Context Steerability Across Diverse Perspectives

Read the original on arXiv Machine Learning →

The paper investigates how post‑training fine‑tuning of large language models can reduce their ability to adapt to in‑context information, particularly when the models are fine‑tuned toward one side of cultural‑value disagreements. Experiments show that as a model is trained to favor a specific perspective, its capacity to recognize and enact opposing viewpoints diminishes over time. The authors propose an alternative objective that balances reward maximization with a prescribed distribution over expressed perspectives, offering a practical stance‑distribution matching implementation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computation and Language
Sep 10

Deep and shallow biases in language models

The paper introduces a bias depth score to differentiate between stable model preferences (Deep biases) and prompt‑dependent responses (Shallow biases) in large language models. By analyzing 4,442 opinion prompts across four models, it finds that only about a quarter of concentrated preferences persist after scenario reframing, indicating that most are shallow. The study shows Deep biases are more often inherited from pretraining and harder to remove through fine‑tuning or prompt‑based debiasing, highlighting the need to distinguish learned biases from prompt artifacts.

By An Vo, Vy Tuong Dang, Khai-Nguyen Nguyen, Emilio Villa-Cueva, Thamar Solorio, Anh Totti Nguyen, Daeyoung Kim
llmsfine-tuningsafety
More like this →
arXiv Computation and Language
Aug 31

CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia

arXiv:2608.28405v1 Announce Type: new Abstract: Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common...

By Bryan Chen Zhengyu Tan, Weihua Zheng, Thong T. Doan, Bich Ngoc Doan, Jia Wang Peh, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Zhengyuan Liu, JinYeong Bak, Wafi Shamdi, Soo Kai Chie, Liew Yu Siong, Aina Azyyati Binti Mohamad Rezal, Lew Yan Yan Vanessa, Huadan Wu, Dylan Raharja, Nadya Yuki Wangsajaya, Akane Fukushige, Kazushi Kato, Koji Inoue, Tatsuya Kawahara, Jaehyung Seo, Dongjun Kim, Seungyoon Lee, Zi Haur Pang, Rui Yang Tan, Charibeth Ko Cheng, Maria Regina Justina Estuar, Jann Railey Montalan, Pham Minh Duc, Roy Ka-Wei Lee
llmsfine-tuningbenchmarkssafety
More like this →
arXiv AI
Sep 30

Population Fidelity: Evaluating Population Representativeness in LLMs

The paper introduces Population Fidelity, an evaluation framework for assessing how well large language models (LLMs) represent human population attitudes. It focuses on three dimensions: group-level accuracy, between-group variation, and the structure of that variation. Using the framework, the authors replicate a prior study on machine bias and test cultural fine-tuning, finding that while fine-tuning improves overall alignment, it does not enhance representation of within-population differences.

By Neemias B. da Silva, Martin Lukk, Ali Sutani, Abhishek Moturu, Harris Yang, Daniel Silver, Matt Ratto, Thiago H. Silva
llmsfine-tuningsafety
More like this →