Connor Baumler, Calvin Bao, Huy Nghiem, Xinchen Yang, Marine Carpuat, Hal Daumé Iii. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

WARNING: This paper contains examples of offensive materials.To address toxic content on social media, we introduce SMARTER, a data-efficient 2-stage framework for explainable content moderation using Large Language Models (LLMs).In Stage 1, we leverage LLMs' own outputs to generate synthetic explanations for correct and incorrect labels, enabling preference optimization with minimal supervision.In Stage 2, we refine explanation quality through cross-model training, allowing weaker models to align with stronger ones.Experiments on 3 classification tasks (HateXplain, Latent Hate, Implicit Hate) show SMARTER achieves up to 13% macro-F1 improvement over few-shot baselines using only 6-57% of training data.Our framework offers a scalable strategy for low-data settings by harnessing LLMs' selfimprovement for explainable moderation.

Large Language Models (LLMs) are increasingly involved in high-stakes domains, yet how they reason about socially-sensitive decisions still remains underexplored.We present a largescale audit of LLMs' treatment of socioeconomic status (SES) in college admissions decisions using a novel dual-process framework inspired by cognitive science.Leveraging a synthetic dataset of 30,000 applicant profiles 1 grounded in real-world correlations, we prompt 4 open-source LLMs (Qwen 2, Mistral v0.3, Gemma 2, Llama 3.1) under 2 modes: a fast, decision-only setup (System 1) and a slower, explanation-based setup (System 2).Results from 5 million prompts reveals that LLMs consistently favor low-SES applicants-even when controlling for academic performance-and that System 2 amplifies this tendency by explicitly invoking SES as compensatory justification, highlighting both their potential and volatility as decision-makers.We then propose DPAF, a dual-process audit framework to probe LLMs' reasoning behaviors in sensitive applications.

The propagation of offensive content through social media channels has garnered attention of the research community.Multiple works have proposed various semantically related yet subtle distinct categories of offensive speech.In this work, we explore meta-learning approaches to leverage the diversity of offensive speech corpora to enhance their reliable and efficient detection.We propose a joint embedding architecture that incorporates the input's label and definition for classification via Prototypical Network.Our model achieves at least 75% of the maximal F1-score while using less than 10% of the available training data across 4 datasets.Our experimental findings also provide a case study of training strategies valuable to combat resource scarcity.

Social science research has shown that candidates with names indicative of certain races or genders often face discrimination in employment practices.Similarly, Large Language Models (LLMs) have demonstrated racial and gender biases in various applications.In this study, we utilize GPT-3.5-Turbo and Llama 3-70B-Instruct to simulate hiring decisions and salary recommendations for candidates with 320 first names that strongly signal their race and gender, across over 750,000 prompts.Our empirical results indicate a preference among these models for hiring candidates with White female-sounding names over other demographic groups across 40 occupations.Additionally, even among candidates with identical qualifications, salary recommendations vary by as much as 5% between different subgroups.A comparison with real-world labor data reveals inconsistent alignment with U.S. labor market characteristics, underscoring the necessity of risk investigation of LLM-powered systems.