Related papers: Negotiative Alignment: Embracing Disagreement to Achieve Fairer Outcomes -- Insights from Urban Studies

Related papers

PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback [101.62446136707372]
We present a benchmark for multi-turn diagram generation containing 292 images annotated with 3,518 user requirements.<n>PaperBananaBench identifies unsatisfied requirements and converts k of them into natural language feedback.<n>We introduce PaperBanana-Interact, a multi-agent system that refines diagrams via an internal critique-and-refine loop.
arXiv Detail & Related papers (2026-08-31T04:52:32Z)
Whose Assessment of Distress? Community Perspectives and LLM Alignment on Well-Being Posts [4.801119915366712]
Large language models (LLMs) used for distress detection are typically aligned to a single, undifferentiated standard.<n>How well do these models capture the perspectives of the communities whose language they assess?<n>We evaluate nine open-weight LLM configurations and four frontier configurations against these labels.
arXiv Detail & Related papers (2026-08-29T21:23:57Z)
Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist [69.81453995715673]
Existing faithfulness benchmarks rely on simple atomic instructions.<n>We introduce Arena-T2I Hard, a 310-prompt stress benchmark drawn from real arena T2I logs.<n>We propose a dependency-aware checklist reward that decomposes each prompt into a DAG of yes/no questions and zeroes descendants of failed parents.
arXiv Detail & Related papers (2026-06-30T14:17:05Z)
Knowledge Index of Noah's Ark [63.143852586221534]
We introduce KINA, an 899-item benchmark across 261 fine-grained disciplines.<n>We prove a bonus-on-bar tournament weakly FOSD-dominates flat payment in released-review quality.<n>The top model, Gemini-3.1-Pro-Preview, reaches 53.17%, followed by Claude-Opus-4.6 at 49.92% and GPT-5.4 at 48.55%.
arXiv Detail & Related papers (2026-06-03T17:06:49Z)
Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment [75.88231994139132]
We show that even state-of-the-art models like GPT-4.1 achieve only 57.4% accuracy in predicting modal preferences.<n>We find significant pre-existing performance biases, where models better emulate young, male, Chinese, and Christian personas.
arXiv Detail & Related papers (2026-04-14T15:06:13Z)
Fair Learning for Bias Mitigation and Quality Optimization in Paper Recommendation [1.9029881798999504]
We present a MultiLayer Perceptron (MLP)-based model that addresses demographic disparities in post-review paper acceptance decisions.<n>Our methodology penalizes demographic disparities while preserving quality throughal criteria (e.g., race, country) and a customized fairness loss.
arXiv Detail & Related papers (2026-03-12T13:48:29Z)
From Bias to Balance: Fairness-Aware Paper Recommendation for Equitable Peer Review [1.9029881798999504]
We propose a framework for post-review paper selection that preserves, and in some settings can even enhance, measured scholarly quality.<n>By first analyzing the behavior of the fairness parameters under controlled conditions and then validating them on real submissions, Fair-PaperRec offers a practical, equity-focused framework for post-review paper selection that preserves, and in some settings can even enhance, measured scholarly quality.
arXiv Detail & Related papers (2026-02-25T21:57:07Z)
Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework [0.31497178896386996]
HUMAINE is a framework for multidimensional, demographically aware measurement of human-AI interaction.<n>We evaluate 28 state-of-the-art models across five human-centric dimensions.
arXiv Detail & Related papers (2026-02-03T09:51:47Z)
Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior [9.90941081429899]
Large language models (LLMs) are increasingly trained using human feedback for safety and alignment with human values.<n>This study examines how incorporating pluralistic values affects LLM behavior by systematically evaluating demographic variation and design parameters in the alignment pipeline.
arXiv Detail & Related papers (2025-11-18T13:14:42Z)
Fortytwo: Swarm Inference with Peer-Ranked Consensus [36.94429692322632]
We present Fortytwo, a novel protocol that leverages swarm intelligence principles and distributed pairwise ranking consensus to achieve superior performance in AI inference.<n>Using pairwise ranking with a custom Bradley-Terry-style aggregation model, we demonstrate that swarm inference substantially outperforms majority voting.
arXiv Detail & Related papers (2025-10-27T23:19:48Z)
Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges [47.14342587731284]
This survey provides a comprehensive overview of alignment techniques, training protocols, and empirical findings in large language models (LLMs) alignment.<n>We analyze the development of alignment methods across diverse paradigms, characterizing the fundamental trade-offs between core alignment objectives.<n>We discuss state-of-the-art techniques, including Direct Preference Optimization (DPO), Constitutional AI, brain-inspired methods, and alignment uncertainty quantification (AUQ)
arXiv Detail & Related papers (2025-07-25T20:52:58Z)
PRIDE -- Parameter-Efficient Reduction of Identity Discrimination for Equality in LLMs [0.0552480439325792]
Large Language Models (LLMs) frequently reproduce the gender- and sexual-identity prejudices embedded in their training corpora.<n>We evaluate two parameter-efficient fine-tuning (PEFT) techniques - Low-Rank Adaptation (LoRA) and soft-prompt tuning.<n>Fine-tuning with LoRA reduces those scores by up to 50 points and raises neutrality from virtually 0% to as much as 36%.
arXiv Detail & Related papers (2025-07-18T08:44:27Z)
A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs [10.655783463895325]
Large language models (LLMs) exhibit a pronounced WEIRD (Western, Educated, Industrialized, Rich, Democratic) cultural bias.<n>This monocultural perspective may reinforce dominant values and marginalize diverse cultural viewpoints.<n>We introduce a systematic framework designed to boost fair and robust cross-cultural consensus.
arXiv Detail & Related papers (2025-06-16T08:42:39Z)
The Leaderboard Illusion [61.27964089648608]
Arena has emerged as the go-to leaderboard for ranking the most capable AI systems.<n>We identify systematic issues that have resulted in a distorted playing field.
arXiv Detail & Related papers (2025-04-29T15:48:49Z)
Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models [66.5536396328527]
LLMs inadvertently absorb spurious correlations from training data, leading to stereotype associations between biased concepts and specific social groups.<n>We propose Fairness Mediator (FairMed), a bias mitigation framework that neutralizes stereotype associations.<n>Our framework comprises two main components: a stereotype association prober and an adversarial debiasing neutralizer.
arXiv Detail & Related papers (2025-04-10T14:23:06Z)
Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness [61.45587642780908]
We propose a three-step approach for parameter-efficient fine-tuning of image-text foundation models.<n>Our method improves its two key components: minority samples identification and the robust training algorithm.<n>Our theoretical analysis shows that our PPA enhances minority group identification and is Bayes optimal for minimizing the balanced group error.
arXiv Detail & Related papers (2025-03-12T15:46:12Z)
Decoding Safety Feedback from Diverse Raters: A Data-driven Lens on Responsiveness to Severity [27.898678946802438]
We introduce a novel data-driven approach for interpreting granular ratings in pluralistic datasets.<n>We distill non-parametric responsiveness metrics that quantify the consistency of raters in scoring varying levels of the severity of safety violations.<n>We show that our approach can inform rater selection and feedback interpretation by capturing nuanced viewpoints across different demographic groups.
arXiv Detail & Related papers (2025-03-07T17:32:31Z)
Urban Safety Perception Through the Lens of Large Multimodal Models: A Persona-based Approach [4.315451628809687]
This study introduces Large Multimodal Models (LMMs), specifically Llava 1.6 7B, as a novel approach to assess safety perceptions of urban spaces. The model achieved an average F1-score of 59.21% in classifying urban scenarios as safe or unsafe. incorporating Persona-based prompts revealed significant variations in safety perceptions across the socio-demographic groups of age, gender, and nationality.
arXiv Detail & Related papers (2025-03-01T20:34:30Z)
The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems [1.137572571250676]
We argue that implicit consensus, where agents exchange information yet independently form decisions via in-context learning, can be more effective in dynamic environments. We formalize a consensus-diversity tradeoff, showing conditions where implicit methods outperform explicit ones. We highlight emergent coordination via in-context learning, underscoring the value of preserving diversity for resilient decision-making.
arXiv Detail & Related papers (2025-02-23T13:12:53Z)
The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models [91.86718720024825]
We center transgender, nonbinary, and other gender-diverse identities to investigate how alignment procedures interact with pre-existing gender-diverse bias.<n>Our findings reveal that DPO-aligned models are particularly sensitive to supervised finetuning.<n>We conclude with recommendations tailored to DPO and broader alignment practices.
arXiv Detail & Related papers (2024-11-06T06:50:50Z)
Democratizing Reward Design for Personal and Representative Value-Alignment [10.1630183955549]
We introduce Interactive-Reflective Dialogue Alignment, a method that iteratively engages users in reflecting on and specifying their subjective value definitions. This system learns individual value definitions through language-model-based preference elicitation and constructs personalized reward models. Our findings demonstrate diverse definitions of value-aligned behaviour and show that our system can accurately capture each person's unique understanding.
arXiv Detail & Related papers (2024-10-29T16:37:01Z)
EARN Fairness: Explaining, Asking, Reviewing, and Negotiating Artificial Intelligence Fairness Metrics Among Stakeholders [5.216732191267959]
We propose a new framework, EARN Fairness, which facilitates collective metric decisions among stakeholders without requiring AI expertise.<n>The framework features an adaptable interactive system and a stakeholder-centered EARN Fairness process to explain fairness metrics, Ask stakeholders' personal metric preferences, Review metrics collectively, and Negotiate a consensus on metric selection.<n>Our work shows that the EARN Fairness framework enables stakeholders to express personal preferences and reach consensus, providing practical guidance for implementing human-centered AI fairness in high-risk contexts.
arXiv Detail & Related papers (2024-07-16T07:20:30Z)
The Impossibility of Fair LLMs [17.812295963158714]
We analyze a variety of technical fairness frameworks and find inherent challenges in each that make the development of a fair language model intractable.<n>We show that each framework either does not extend to the general-purpose AI context or is infeasible in practice.<n>These inherent challenges would persist for general-purpose AI, including LLMs, even if empirical challenges, such as limited participatory input and limited measurement methods, were overcome.
arXiv Detail & Related papers (2024-05-28T04:36:15Z)
Persona Inconstancy in Multi-Agent LLM Collaboration: Conformity, Confabulation, and Impersonation [16.82101507069166]
Multi-agent AI systems can be used for simulating collective decision-making in scientific and practical applications. We examine AI agent ensembles engaged in cross-national collaboration and debate by analyzing their private responses and chat transcripts. Our findings suggest that multi-agent discussions can support collective AI decisions that more often reflect diverse perspectives.
arXiv Detail & Related papers (2024-05-06T21:20:35Z)
Disciplining Deliberation: A Sociotechnical Perspective on Machine Learning Trade-offs [0.0]
Two prominent trade-offs in artificial intelligence are between predictive accuracy and fairness, and between predictive accuracy and interpretability. prevailing interpretation views these formal trade-offs as directly corresponding to tensions between underlying social values. I introduce a sociotechnical approach to examining the value implications of trade-offs.
arXiv Detail & Related papers (2024-03-07T05:03:18Z)
AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents [65.16893197330589]
Large Language Models (LLMs) have demonstrated their ability to replicate human behaviors across a wide range of scenarios. However, their capability in handling complex, multi-character social interactions has yet to be fully explored. We introduce the Multi-Agent Interaction Evaluation Framework (AntEval), encompassing a novel interaction framework and evaluation methods.
arXiv Detail & Related papers (2024-01-12T11:18:00Z)
GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives [18.574420136899978]
We propose GRASP, a comprehensive disagreement analysis framework to measure group association in perspectives among different rater sub-groups. Our framework reveals specific rater groups that have significantly different perspectives than others on certain tasks, and helps identify demographic axes that are crucial to consider in specific task contexts.
arXiv Detail & Related papers (2023-11-09T00:12:21Z)
Evaluating the Social Impact of Generative AI Systems in Systems and Society [43.32010533676472]
Generative AI systems across modalities, ranging from text (including code), image, audio, and video, have broad social impacts. There is no official standard for means of evaluating those impacts or for which impacts should be evaluated. We present a guide that moves toward a standard approach in evaluating a base generative AI system for any modality.
arXiv Detail & Related papers (2023-06-09T15:05:13Z)
Heterogeneous Value Alignment Evaluation for Large Language Models [91.96728871418]
Large Language Models (LLMs) have made it crucial to align their values with those of humans. We propose a Heterogeneous Value Alignment Evaluation (HVAE) system to assess the success of aligning LLMs with heterogeneous values.
arXiv Detail & Related papers (2023-05-26T02:34:20Z)
Social Diversity Reduces the Complexity and Cost of Fostering Fairness [63.70639083665108]
We investigate the effects of interference mechanisms which assume incomplete information and flexible standards of fairness. We quantify the role of diversity and show how it reduces the need for information gathering. Our results indicate that diversity changes and opens up novel mechanisms available to institutions wishing to promote fairness.
arXiv Detail & Related papers (2022-11-18T21:58:35Z)
Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization [73.89239820192894]
We argue that automated counterfactual generation should regard several aspects of the produced adversarial instances. We present a novel framework for the generation of counterfactual examples.
arXiv Detail & Related papers (2022-05-20T15:02:53Z)
Towards a multi-stakeholder value-based assessment framework for algorithmic systems [76.79703106646967]
We develop a value-based assessment framework that visualizes closeness and tensions between values. We give guidelines on how to operationalize them, while opening up the evaluation and deliberation process to a wide range of stakeholders.
arXiv Detail & Related papers (2022-05-09T19:28:32Z)
Spatio-Temporal Graph Representation Learning for Fraudster Group Detection [50.779498955162644]
Companies may hire fraudster groups to write fake reviews to either demote competitors or promote their own businesses. To detect such groups, a common model is to represent fraudster groups' static networks. We propose to first capitalize on the effectiveness of the HIN-RNN in both reviewers' representation learning.
arXiv Detail & Related papers (2022-01-07T08:01:38Z)
Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach [131.20444904674494]
We tackle the problem of measuring group fairness under unawareness of sensitive attributes. We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem.
arXiv Detail & Related papers (2021-09-17T13:45:46Z)
Contrastive Examples for Addressing the Tyranny of the Majority [83.93825214500131]
We propose to create a balanced training dataset, consisting of the original dataset plus new data points in which the group memberships are intervened. We show that current generative adversarial networks are a powerful tool for learning these data points, called contrastive examples.
arXiv Detail & Related papers (2020-04-14T14:06:44Z)
Towards Quantifying the Distance between Opinions [66.29568619199074]
We find that measures based solely on text similarity or on overall sentiment often fail to effectively capture the distance between opinions. We propose a new distance measure for capturing the similarity between opinions that leverages the nuanced observation. In an unsupervised setting, our distance measure achieves significantly better Adjusted Rand Index scores (up to 56x) and Silhouette coefficients (up to 21x) compared to existing approaches.
arXiv Detail & Related papers (2020-01-27T16:01:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.