Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories

• URL: http://arxiv.org/abs/2509.16742v1
• Date: Sat, 20 Sep 2025 17:09:14 GMT
• Title: Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories
• Authors: Mohammad Beigi, Ying Shen, Parshin Shojaee, Qifan Wang, Zichao Wang, Chandan Reddy, Ming Jin, Lifu Huang,
• Abstract summary: We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
• Score: 58.988535279557546
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster \textit{sycophancy}, i.e., the tendency of a model to agree with or reinforce user-provided information even when it's factually incorrect. To address this challenge, we introduce \textbf{SMART} (Sycophancy Mitigation through Adaptive Reasoning Trajectories), which reframes sycophancy as a \textit{reasoning optimization problem} rather than an output alignment issue. SMART is a two-stage framework comprising: (1) Uncertainty-Aware Adaptive Monte Carlo Tree Search (UA-MCTS), which dynamically adjusts model exploration based on state-level uncertainty to collect high-quality, diverse reasoning trajectories alongside both stepwise progress and final outcome rewards; and (2) progress-based reinforcement learning, which fine-tunes the model using the collected trajectories and reward signals to reinforce effective reasoning patterns. Through extensive experiments, we show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs and maintaining general capabilities. These results underscore the importance of optimizing internal reasoning mechanisms to build more truthful and aligned AI assistants.

Related papers

• Dual-Phase LLM Reasoning: Self-Evolved Mathematical Frameworks [48.105258051884384]
  This paper proposes a new two-stage training framework that enhances models' self-correction capabilities.<n>During the first stage, a multi-turn dialogue strategy guides the model to generate long chain-of-thought (CoT) data.<n>The second stage employs a difficulty-aware rejection sampling mechanism to dynamically optimize data distribution.
  arXiv  Detail & Related papers  (2026-01-09T08:19:11Z)
• Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing [70.35701681177655]
  Self-improvement has emerged as a mainstream paradigm for advancing the reasoning capabilities of large vision-language models.<n>We introduce four efficient strategies to achieve head-tail re-balancing during the exploration-and-learning self-improvement process.<n>Our methods consistently improve visual reasoning capabilities, outperforming vanilla self-improvement by 3.86 points on average.
  arXiv  Detail & Related papers  (2025-10-30T13:26:58Z)
• Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency [4.047219770183742]
  Time series forecasting plays a pivotal role in critical domains such as energy management and financial markets.<n>This study reveals a counterintuitive phenomenon: appropriately truncating historical data can enhance prediction accuracy.<n>We propose an innovative solution termed Adaptive Masking Loss with Representation Consistency.
  arXiv  Detail & Related papers  (2025-10-22T19:23:53Z)
• RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning [27.235259453535537]
  RationAnomaly is a novel framework that enhances log anomaly detection by synergizing Chain-of-Thought fine-tuning with reinforcement learning.<n>We have released the corresponding resources, including code and datasets.
  arXiv  Detail & Related papers  (2025-09-18T07:35:58Z)
• Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement [101.77467538102924]
  Large reasoning models (LRMs) exhibit overthinking, which hinders efficiency and inflates inference cost.<n>We propose two lightweight methods to enhance LRM efficiency.<n>First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction.<n>Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity.
  arXiv  Detail & Related papers  (2025-06-18T17:18:12Z)
• AIMatDesign: Knowledge-Augmented Reinforcement Learning for Inverse Materials Design under Data Scarcity [5.660883851948541]
  AIMatDesign is a reinforcement learning framework for inverse design methods.<n>It builds a trusted experience pool and accelerates model convergence.<n>It significantly surpasses traditional machine learning and reinforcement learning methods in discovery efficiency, convergence speed, and success rates.
  arXiv  Detail & Related papers  (2025-06-17T08:17:44Z)
• The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models [63.98194996746229]
  Large language models (LLMs) have significantly advanced in reasoning tasks through reinforcement learning (RL) optimization.<n>However, reasoning-oriented RL fine-tuning significantly increases the prevalence of hallucinations.<n>We propose Factuality-aware Step-wise Policy Optimization (FSPO), an innovative RL fine-tuning algorithm incorporating explicit factuality verification.
  arXiv  Detail & Related papers  (2025-05-30T14:23:32Z)
• Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration [15.711365331854614]
  We introduce Dynamic Adaptation of Reasoning Trajectories (DART), a novel data adaptation framework.<n>Instead of uniformly imitating expert steps, DART employs a selective imitation strategy guided by step-wise adaptability estimation.<n>We validate DART across multiple reasoning benchmarks and model scales, demonstrating that it significantly improves generalization and data efficiency.
  arXiv  Detail & Related papers  (2025-05-27T04:08:11Z)
• LARES: Latent Reasoning for Sequential Recommendation [96.26996622771593]
  We present LARES, a novel and scalable LAtent REasoning framework for Sequential recommendation.<n>Our proposed approach employs a recurrent architecture that allows flexible expansion of reasoning depth without increasing parameter complexity.<n>Our framework exhibits seamless compatibility with existing advanced models, further improving their recommendation performance.
  arXiv  Detail & Related papers  (2025-05-22T16:22:54Z)
• Sycophancy in Vision-Language Models: A Systematic Analysis and an Inference-Time Mitigation Framework [18.54098084470481]
  We analyze sycophancy across vision-language benchmarks and propose an inference-time mitigation framework.<n>Our framework effectively mitigates sycophancy across all evaluated models, while maintaining performance on neutral prompts.
  arXiv  Detail & Related papers  (2024-08-21T01:03:21Z)
• InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling [66.3072381478251]
  Reward hacking, also termed reward overoptimization, remains a critical challenge. We propose a framework for reward modeling, namely InfoRM, by introducing a variational information bottleneck objective. We show that InfoRM's overoptimization detection mechanism is not only effective but also robust across a broad range of datasets.
  arXiv  Detail & Related papers  (2024-02-14T17:49:07Z)

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.