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.
arXiv:2609.00565v1 Announce Type: cross Abstract: Cultural fine-tuning has become the de facto paradigm for building culture-aware large language models (LLMs), yet existing optimization exclusively...
arXiv:2511. 06148v4 Announce Type: replace-cross Abstract: As large language models (LLMs) are adopted into frameworks that grant them the capacity to make real decisions, it is increasingly important to ensure that they are unbiased.
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.
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...
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.
arXiv:2608.29610v1 Announce Type: new Abstract: The current alignment tuning paradigm for Large Language Models (LLMs) prioritizes surface-level behaviors -- fluency, safety, and tonal consistency. W...
arXiv:2609.10253v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in globally used assistants, yet their default choices in culturally grounded everyday situation...
arXiv:2605. 28882v2 Announce Type: replace-cross Abstract: With the rapid advancement of large language models, evaluating human-likeness in open-ended conversation has become increasingly important.
arXiv:2603.08275v2 Announce Type: replace-cross Abstract: With the global proliferation of Large Language Models (LLMs), cultural safety, defined as the ability to generate respectful and appropriate...
The paper presents a unified evaluation of cross‑lingual consistency (CLC) enhancement methods for multilingual language models, covering inference‑time interventions and post‑training approaches across three model families and three closed‑form benchmarks. Results indicate that post‑training methods, especially direct distribution alignment, consistently improve CLC across all model‑dataset combinations, while other methods are more sensitive to answer format and language coverage. The study also examines the impact of CLC enhancement on culturally diverse question answering, finding no systematic degradation in controlled settings but occasional accuracy drops in open‑ended generation, particularly for non‑English responses.
arXiv:2607. 19345v1 Announce Type: cross Abstract: Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, and extending them to long-context settings has emerged as an important frontier.
The paper investigates whether large language models (LLMs) possess intrinsic value systems and how to quantify and align them. By projecting responses from 106 LLMs and 95,000 human survey profiles into a shared sociological space, the authors confirm that LLMs do have values, though these values form a concentrated, idealized core rather than mirroring human diversity. They introduce the Prior-Environment-Cognition (PEC) framework to mathematically define value expression and propose an adaptive Alignment Prescription that identifies minimal interventions—ranging from prompts to targeted parameter updates—to steer LLM values efficiently without harming general performance.