Objective Decoupling in Social Reinforcement Learning: Recovering Ground Truth from Sycophantic Majorities

• URL: http://arxiv.org/abs/2602.08092v1
• Date: Sun, 08 Feb 2026 19:23:02 GMT
• Title: Objective Decoupling in Social Reinforcement Learning: Recovering Ground Truth from Sycophantic Majorities
• Abstract summary: We show that Dogma 4 of Reinforcement Learning fails in social settings where evaluators may be sycophantic, lazy, or adversarial.<n>We propose Epistemic Source Alignment (ESA) to resolve this problem.<n>ESA utilizes sparse safety axioms to judge the source of the feedback rather than the signal itself.
• Score: 1.3428344011390776
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Contemporary AI alignment strategies rely on a fragile premise: that human feedback, while noisy, remains a fundamentally truthful signal. In this paper, we identify this assumption as Dogma 4 of Reinforcement Learning (RL). We demonstrate that while this dogma holds in static environments, it fails in social settings where evaluators may be sycophantic, lazy, or adversarial. We prove that under Dogma 4, standard RL agents suffer from what we call Objective Decoupling, a structural failure mode where the agent's learned objective permanently separates from the latent ground truth, guaranteeing convergence to misalignment. To resolve this, we propose Epistemic Source Alignment (ESA). Unlike standard robust methods that rely on statistical consensus (trusting the majority), ESA utilizes sparse safety axioms to judge the source of the feedback rather than the signal itself. We prove that this "judging the judges" mechanism guarantees convergence to the true objective, even when a majority of evaluators are biased. Empirically, we show that while traditional consensus methods fail under majority collusion, our approach successfully recovers the optimal policy.

Related papers

• \mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments [21.69919643934826]
  Decentralized machine learning often relies on outsourcing computations, such as evaluations, to untrusted worker nodes.<n>We study this adversary-dominated setting through an incentive-oriented framework in which reports are accepted and rewarded only when they are mutually consistent up to a threshold.<n>We propose mathsfVISTA, an adaptive algorithm that tunes the acceptance threshold using the optimization history.
  arXiv  Detail & Related papers  (2026-05-08T15:07:15Z)
• Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation [19.888565537472363]
  CoRM-RAG (Counterfactual Risk Minimization for RAG) is a framework that aligns retrieval with decision safety rather than mere similarity.<n>We introduce a Cognitive Perturbation Protocol to simulate user biases during training, which is then distilled into a lightweight Evidence Critic.<n>This scoring module learns to identify documents that possess sufficient evidential strength to steer the model toward correctness despite adversarial query perturbations.
  arXiv  Detail & Related papers  (2026-05-02T07:22:24Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Learning When to Trust in Contextual Bandits [1.3428344011390776]
  We term this mode as Contextual Sycophancy, where evaluators are truthful in benign contexts but strategically biased in critical ones.<n>We propose CESA-LinUCB, which learns a high-dimensional Trust Boundary for each evaluator.<n>We prove that CESA-LinUCB achieves sublinear regret $tildeO(sqrtT)$ against contextual adversaries, recovering the ground truth even when no evaluator is globally reliable.
  arXiv  Detail & Related papers  (2026-03-09T01:35:37Z)
• ALIVE: Awakening LLM Reasoning via Adversarial Learning and Instructive Verbal Evaluation [4.265094703231012]
  We introduce textbfALIVE (emphAdrial Learning with Instructive Verbal Evaluation), a hands-free alignment framework.<n>By coupling adversarial learning with instructive verbal feedback, ALIVE enables models to internalize evaluative criteria directly from raw corpora.<n>With identical data and compute, ALIVE achieves markedly improved cross-domain generalization, and higher self-correction rates.
  arXiv  Detail & Related papers  (2026-02-05T09:20:23Z)
• A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness [57.510025257780306]
  We show that existing validation protocols fail to account for substantial distribution shifts inherent to red-teaming.<n>We propose ReliableBench, a benchmark of behaviors that remain more consistently judgeable, and JudgeStressTest, a dataset designed to expose judge failures.
  arXiv  Detail & Related papers  (2026-02-04T15:13:35Z)
• Making Bias Non-Predictive: Training Robust LLM Judges via Reinforcement Learning [91.8584139564909]
  Large language models (LLMs) increasingly serve as automated judges, yet they remain susceptible to cognitive biases.<n>We propose Epistemic Independence Training (EIT), a reinforcement learning framework grounded in a key principle.<n>EIT operationalizes this through a balanced conflict strategy where bias signals are equally likely to support correct and incorrect answers.
  arXiv  Detail & Related papers  (2026-02-02T01:43:48Z)
• When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards [20.896576101848655]
  We study whetherReinforcement Learning with Verifiable Rewards elicits novel capabilities or merely sharpens the distribution over existing knowledge.<n>We propose inverse-success advantage calibration to prioritize difficult queries and distribution-level calibration to diversify sampling via a memory network.
  arXiv  Detail & Related papers  (2026-01-22T03:15:57Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency [78.91846841708586]
  We show that even facts answered with perfect self-consistency can rapidly collapse under mild contextual interference.<n>We propose Neighbor-Consistency Belief (NCB), a structural measure of belief that evaluates response coherence across a conceptual neighborhood.<n>We also present Structure-Aware Training (SAT), which optimize context-invariant belief structure and reduces long-tail knowledge brittleness by approximately 30%.
  arXiv  Detail & Related papers  (2026-01-09T16:23:21Z)
• Aletheia: Quantifying Cognitive Conviction in Reasoning Models via Regularized Inverse Confusion Matrix [0.6345523830122167]
  We extend Simhi's CHOKE phenomenon to quantify "Cognitive Conviction" in System 2 reasoning models.<n>We propose Project Aletheia, a cognitive physics framework that employs Tikhonov Regularization to invert the judge's confusion matrix.<n>This work serves as a blueprint for measuring AI scientific integrity.
  arXiv  Detail & Related papers  (2026-01-04T13:57:32Z)
• BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts [69.7477004390211]
  We formalize two core acts Adversarial and Alignment, and operationalize them via probabilistic constraints on what an agent may generate.<n>We instantiate this idea in BEDA, a framework that consists of the world set, the belief estimator for belief estimation, and the conditional generator that selects acts and realizes utterances consistent with the inferred beliefs.
  arXiv  Detail & Related papers  (2025-12-31T14:26:55Z)
• The Silent Scholar Problem: A Probabilistic Framework for Breaking Epistemic Asymmetry in LLM Agents [0.6117371161379209]
  We propose a formal probabilistic framework that provides agents with a non-altruistic motive for bidirectional knowledge exchange.<n>We show how these accumulated belief states serve as verifiable reward signals for Reinforcement Learning from Human Feedback (RLHF) and high-quality data filters for Supervised Fine-Tuning (SFT)<n> Simulation results validate that this uncertainty-driven strategy significantly outperforms random baselines in heterogeneous environments.
  arXiv  Detail & Related papers  (2025-12-24T02:02:25Z)
• On Minimizing Adversarial Counterfactual Error in Adversarial RL [18.044879441434432]
  adversarial noise poses significant risks in safety-critical scenarios.<n>We introduce a novel objective called Adversarial Counterfactual Error (ACoE)<n>Our method significantly outperforms current state-of-the-art approaches for addressing adversarial RL challenges.
  arXiv  Detail & Related papers  (2024-06-07T08:14:24Z)
• From Mean to Extreme: Formal Differential Privacy Bounds on the Success of Real-World Data Reconstruction Attacks [54.25638567385662]
  Differential Privacy in machine learning is often interpreted as guarantees against membership inference.<n> translating DP budgets into quantitative protection against the more damaging threat of data reconstruction remains a challenging open problem.<n>This paper bridges the critical gap by deriving the first formal privacy bounds tailored to the mechanics of demonstrated "from-scratch" attacks.
  arXiv  Detail & Related papers  (2024-02-20T09:52:30Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)

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.