arXiv AI October 19, 2026 By Basar Demir, Emily Shen, Ksheeraj Sai Vepuri, Sourabh Kulkarni, Harihar Subramanyam, Ankit Jain, Nan Jiang, Chirag Nagpal

Aligning Language Models Towards Counterfactual Invariance

Read the original on arXiv AI →

The paper investigates how small changes in prompt characteristics, such as demographic attributes, can alter the semantics and tone of large language model outputs. It shows that standard alignment methods like reinforcement learning can worsen counterfactual bias by increasing response quality differences across demographics. To mitigate this, the authors propose a policy‑gradient approach with a group‑level reward that operates on matched counterfactual prompt pairs, and they validate its effectiveness on fairness benchmarks while maintaining overall response quality.

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 AI.

arXiv Machine Learning

Jul 31

Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization

arXiv:2604. 07343v2 Announce Type: replace-cross Abstract: Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values.

By Qiyao Ma, Dechen Gao, Rui Cai, Boqi Zhao, Hanchu Zhou, Junshan Zhang, Zhe Zhao

llms reinforcement-learning benchmarks safety

arXiv Machine Learning

Aug 4

Inference-Time Policy Alignment for Fair Reinforcement Learning

arXiv:2608. 00175v1 Announce Type: new Abstract: Deep reinforcement learning (RL) agents achieve strong performance by optimizing scalar reward functions.

By Umer Siddique, Peilang Li, Conor Wallace, Yongcan Cao

llms agents reinforcement-learning safety

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

llms fine-tuning safety

arXiv AI

Jul 10

Adaptive Generation of Bias-Eliciting Questions for LLMs

arXiv:2510. 12857v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions of users worldwide.

By Robin Staab, Jasper Dekoninck, Maximilian Baader, Martin Vechev

llms benchmarks safety

arXiv AI

Jul 7

Unbiased Alignment for Large Language Models with Noisy Preferences

arXiv:2607. 03248v1 Announce Type: cross Abstract: The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimization.

By Jialiang Wang, Xianming Liu, Xiong Zhou, Hui Liu, Haoliang Li

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 9

A Regret Minimization Framework on Preference Learning in Large Language Models

arXiv:2606. 09124v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has enabled progress on reasoning-intensive tasks by relying on task-specific verifiers that provide automated correctness signals.

By Suhwan Kim, Taehyun Cho, Geon-Hyeong Kim, Yu Jin Kim, Youngsoo Jang, Moontae Lee, Jungwoo Lee

llms reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization

Inference-Time Policy Alignment for Fair Reinforcement Learning

Population Fidelity: Evaluating Population Representativeness in LLMs

Adaptive Generation of Bias-Eliciting Questions for LLMs

Unbiased Alignment for Large Language Models with Noisy Preferences

A Regret Minimization Framework on Preference Learning in Large Language Models