mlsanityData to 7 Oct 2026

AGR: Age Group fairness Reward for Bias Mitigation in LLMs

arXiv 2409.04340 ↗First posted 6 Sep 2024cs.LG cs.AI cs.CLcited by 12

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

LLMs can exhibit age biases, resulting in unequal treatment of individuals across age groups. While much research has addressed racial and gender biases, age bias remains little explored. The scarcity of instruction-tuning and preference datasets for age bias hampers its detection and measurement, and existing fine-tuning methods seldom address age-related fairness. In this paper, we construct age bias preference datasets and instruction-tuning datasets for RLHF. We introduce ARG, an age fairness reward to reduce differences in the response quality of LLMs across different age groups. Extensive experiments demonstrate that this reward significantly improves response accuracy and reduces performance disparities across age groups. Our source code and datasets are available at the anonymous hrefhttps://anonymous.4open.science/r/FairRLHF-D445/readme.mdlink.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 20 of its 25 references that are in the map. First posted on arXiv 6 Sep 2024.

Builds on

20 of 25 references.

Closest ancestors · 1

Same direction, newest first

  1. 2020Learning to summarize from human feedback2 Sep

Other references · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  8. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  9. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  10. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
  11. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  12. 2023ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Modelscited by 184
7 more
  1. 2023Evaluating and Mitigating Discrimination in Language Model Decisionscited by 117
  2. 2019Attenuating Bias in Word Vectorscited by 64
  3. 2024Social Bias Evaluation for Large Language Models Requires Prompt Variationscited by 39
  4. 2023Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Modelscited by 32
  5. 2023Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventionscited by 28
  6. 2023Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projectioncited by 25
  7. 2023Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Modelscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 3.

12 papers.

  1. 2025Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignmentcited by 20
  2. 2024PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximizationcited by 17
  3. 2025PluralLLM: Pluralistic Alignment in LLMs via Federated Learningcited by 14
  4. 2025Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMscited by 5
  5. 2025EcoAlign: An Economically Rational Framework for Efficient LVLM Alignmentcited by 5
  6. 2026When LLMs Imagine People: A Human-Centered Persona Brainstorm Audit for Bias and Fairness in Creative Applicationscited by 2
  7. 2025A Reward-driven Automated Webshell Malicious-code Generator for Red-teamingcited by 1
  8. 2025DMRL: Data- and Model-aware Reward Learning for Data Extractioncited by 0
  9. 2025VisuoAlign: Safety Alignment of LVLMs with Multimodal Tree Searchcited by 0
  10. 2025Information-Dense Reasoning for Efficient and Auditable Security Alert Triagecited by 0
  11. 2026ShellForge: Adversarial Co-Evolution of Webshell Generation and Multi-View Detection for Robust Webshell Defensecited by 0
  12. 2026Membership Inference for Contrastive Pre-training Models with Text-only PII Queriescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024How far can bias go? Tracing bias from pretraining data to alignment
  2. 2025FairCoder: Probing LLM Bias in High-Stakes Decision Making via Coding Tasks
  3. 2024With a Grain of SALT: Are LLMs Fair Across Social Dimensions?
  4. 2025Towards Large Language Models that Benefit for All: Benchmarking Group Fairness in Reward Models
  5. 2025GenderBench: Evaluation Suite for Gender Biases in LLMs
  6. 2025Detecting Prefix Bias in LLM-based Reward Models
  7. 2023Bias Testing and Mitigation in LLM-based Code Generation
  8. 2026Quantifying and Mitigating Self-Preference Bias of LLM Judges