Reproducing FACTER: Fairness via Conformal Thresholding and Prompt Repair

• URL: http://arxiv.org/abs/2606.28620v1
• Date: Fri, 26 Jun 2026 21:37:01 GMT
• Title: Reproducing FACTER: Fairness via Conformal Thresholding and Prompt Repair
• Abstract summary: FACTER is a model-agnostic framework designed to jointly enforce fairness and statistical coverage in recommendation.<n>We conduct a study of the FACTER framework across diverse architectures and dataset sparsity levels.<n>Our analysis shows that FACTER consistently reduces adaptive-threshold violation counts, but that these reductions are not consistently reflected in global fairness metrics.
• Score: 0.6977547772245161
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fayyazi et al. (2025) recently proposed FACTER, a model-agnostic framework designed to jointly enforce fairness and statistical coverage in LLM-based recommendation through conformal thresholding and iterative prompt repair. In this work, we conduct a reproducibility study of the FACTER framework across diverse architectures and dataset sparsity levels, evaluating both the original open-ended generation task and a constrained re-ranking extension. Under the strict reproduction, we observe a divergence in recommendation utility, which we trace to underspecified target-set evaluation in the original study. We then use the constrained re-ranking setting to evaluate FACTER when the candidate set is fixed, and introduce a static Fair Zero-Shot baseline to isolate the contribution of the iterative prompt repair loop. Our analysis shows that FACTER consistently reduces adaptive-threshold violation counts, but that these reductions are not consistently reflected under the fixed threshold or in global fairness metrics. In the constrained ranking setting, static fairness instructions achieve comparable semantic-parity outcomes to FACTER's dynamic repair loop, suggesting that the additional online repair mechanism provides limited benefit in this formulation. All code and reproduction artifacts are available at https://github.com/oscar-omlf/facter-repr.

Related papers

• Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards [6.002323709229882]
  Large language models (LLMs) have been widely applied to automated essay scoring (AES) and automated feedback generation (AFG)<n>We propose RLAES, a unified LLM framework that jointly optimize essay scoring and feedback generation through RL.<n>To make feedback quality measurable, interpretable, and usable for training, we introduce RL-based Feedback Evaluation (RFE)
  arXiv  Detail & Related papers  (2026-07-21T15:49:02Z)
• ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples [65.74946647574696]
  Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs)<n>In this work, we investigate a critical source of this instability: over-optimization.<n>We propose ARMOR, a framework that shifts the paradigm from passive penalty to active sample stabilization.
  arXiv  Detail & Related papers  (2026-07-11T21:22:46Z)
• Non-Parametric Rehearsal Learning via Conditional Mean Embeddings [88.89267783967263]
  We propose a non-parametric rehearsal learning approach for textitavoiding undesired future (AUF) problems.<n>Specifically, we use kernel machinery to reformulate the AUF objective into a unified representation that disentangles desirability modeling from action-induced distributional changes.
  arXiv  Detail & Related papers  (2026-05-09T15:30:52Z)
• Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria [17.272139541614383]
  Auto-Rubric as Reward (ARR) is a framework that reframes reward modeling from implicit weight optimization to explicit, criteria-based decomposition.<n>ARR externalizes a VLM's preference knowledge as prompt-specific gradients, translating holistic intent into independently verifiable quality dimensions.<n>ARR-RPO outperforms pairwise reward models and VLM judges on text-to-image generation and image editing benchmarks.
  arXiv  Detail & Related papers  (2026-05-08T18:05:27Z)
• Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning [47.963236269307735]
  Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation.<n>Current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream generation process.<n>We introduce ReRanking Preference Optimization (RRPO), a reinforcement learning framework that directly aligns reranking with the LLM's generation quality.
  arXiv  Detail & Related papers  (2026-04-02T14:19:47Z)
• PAC-Bayesian Reward-Certified Outcome Weighted Learning [0.0]
  Estimating optimal individualized treatment rules (ITRs) via outcome weighted learning (OWL) often relies on observed rewards that are noisy or optimistic proxies for the true latent utility.<n>We propose PAC-Bayesian Reward-Certified Outcome Weighted Learning (PROWL)<n>Given a one-sided uncertainty certificate, PROWL constructs a conservative reward and a strictly policy-dependent lower bound on the true expected value.
  arXiv  Detail & Related papers  (2026-04-02T12:08:56Z)
• Score-Guided Proximal Projection: A Unified Geometric Framework for Rectified Flow Editing [1.0312968200748118]
  Rectified Flow models achieve state-of-the-art generation quality, yet controlling them for precise tasks remains a challenge.<n>Current approaches bifurcate into inversion-based guidance, which suffers from "geometric locking"<n>We propose Score-Guided Proximal Projection, a unified framework that bridges the gap between deterministic optimization and contraction sampling.
  arXiv  Detail & Related papers  (2026-03-05T23:44:45Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair [4.825037489691159]
  We introduce a post-hoc framework designed to ensure fairness in computer vision systems by combining conformal prediction with a dynamic output repair mechanism.<n>Our approach calculates a fairness-aware non-conformity score that simultaneously assesses prediction errors and fairness violations.<n>When the non-conformity score for a new image exceeds the threshold, FAIR-SIGHT implements targeted corrective adjustments, such as logit shifts for classification and confidence recalibration for detection.
  arXiv  Detail & Related papers  (2025-04-10T02:23:06Z)
• Gumbel Reranking: Differentiable End-to-End Reranker Optimization [61.16471123356738]
  RAG systems rely on rerankers to identify relevant documents.<n> fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs.<n>We propose Gumbel Reranking, an end-to-end training framework for rerankers aimed at minimizing the training-inference gap.
  arXiv  Detail & Related papers  (2025-02-16T13:23:39Z)
• FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems [4.825037489691159]
  We propose FACTER, a fairness-aware framework for LLM-based recommendation systems.<n>By introducing an adaptive semantic variance threshold and a violation-triggered mechanism, FACTER automatically tightens fairness constraints whenever biased patterns emerge.<n> Empirical results on MovieLens and Amazon show that FACTER substantially reduces fairness violations (up to 95.5%) while maintaining strong recommendation accuracy.
  arXiv  Detail & Related papers  (2025-02-05T08:07:04Z)
• Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization [69.07420650261649]
  We introduce a novel, simple, and powerful contrastive MI estimator named as FLO. Empirically, our FLO estimator overcomes the limitations of its predecessors and learns more efficiently. The utility of FLO is verified using an extensive set of benchmarks, which also reveals the trade-offs in practical MI estimation.
  arXiv  Detail & Related papers  (2021-07-02T15:20:41Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.