TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue

• URL: http://arxiv.org/abs/2607.18304v1
• Date: Fri, 17 Jul 2026 05:25:48 GMT
• Title: TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue
• Abstract summary: Supervised fine-tuning can somewhat reduce sycophancy, but relying solely on positive examples is often insufficient to identify and correct failure patterns.<n>We propose the textbfMinimal textbfEdit textbfData textbfAugmentation (MEDA) strategy to construct controlled, stable, minimal edit preference pairs.
• Score: 26.600542246708724
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The sycophancy of large language models can increase the safety risk in intervention dialogue for autistic children. Supervised fine-tuning can somewhat reduce sycophancy, but relying solely on positive examples is often insufficient to identify and correct failure patterns. We observe that sycophancy behaviors can often be localized to a limited span within the model response. In this regime, sequence-level preference optimization can over-update preference-irrelevant tokens and degrade intervention ability. To address this, we propose the \textbf{M}inimal \textbf{E}dit \textbf{D}ata \textbf{A}ugmentation (MEDA) strategy to construct controlled, stable, minimal edit preference pairs and \textbf{T}oken-level \textbf{D}ifference \textbf{D}irect \textbf{P}reference \textbf{O}ptimization (TD-DPO), which upweights difference tokens between chosen and rejected responses while downweighting shared tokens to suppress background drift. Extensive experiments across multiple backbones and evaluators show that TD-DPO achieves a better trade-off between sycophancy mitigation and intervention ability retention in our offline settings, highlighting its potential as a practical alignment approach for autism intervention.

Related papers

• Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models [65.89572755202245]
  Diffusion Language Models (DLMs) offer stronger global awareness and highly parallel generation.<n>Post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient.<n>We propose a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference.
  arXiv  Detail & Related papers  (2026-05-12T09:39:06Z)
• Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models [53.15468578562038]
  We propose an Uncertainty-aware Exploratory Direct Preference Optimization (UE-DPO) method for Multimodal Large Language Models (MLLMs)<n>We first quantify the uncertainty from the model's failure to ground token predictions in the given image.<n>We then encourage more learning pressure on visually deficient tokens in preferred samples, and alleviate the over-penalization of beneficial knowledge in dispreferred samples.
  arXiv  Detail & Related papers  (2026-05-06T13:08:12Z)
• ACPO: Counteracting Likelihood Displacement in Vision-Language Alignment with Asymmetric Constraints [26.309376587678354]
  We propose Asymmetric Constrained Preference Optimization (ACPO)<n>ACPO applies dynamic, target-oriented scaling to preference optimization.<n>We show that ACPO effectively reverses the chosen-reward degradation of standard DPO.
  arXiv  Detail & Related papers  (2026-03-23T16:26:11Z)
• DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding [59.16244104797919]
  We propose **Disagreement-Aware Alignment via Risk-Constrained Decoding (DARC)**.<n>DARC frames response selection as distributionally robust, risk-sensitive decision making.<n>Experiments on alignment benchmarks show that DARC reduces disagreement and tail risk while maintaining competitive average quality.
  arXiv  Detail & Related papers  (2026-03-09T09:21:29Z)
• TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation [0.0]
  Token-weighted, reference-adjusted advantages that prioritize high-value semantic tokens are presented.<n>We evaluate TAB-PO on medical communication annotation.
  arXiv  Detail & Related papers  (2026-02-03T23:48:13Z)
• Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization [78.94590726578014]
  multimodal reasoning models (MLRMs) remain prone to hallucinations, and effective solutions are still underexplored.<n>We propose C3PO, a training-based mitigation framework comprising textbfCompression and textbfPreference textbfOptimization.
  arXiv  Detail & Related papers  (2026-02-03T11:00:55Z)
• Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detection [62.89126207012712]
  Face Presentation Attack Detection (PAD) demands incremental learning to combat spoofing tactics and domains.<n>Privacy regulations forbid retaining past data, necessitating rehearsal-free learning (RF-IL)
  arXiv  Detail & Related papers  (2025-12-22T04:30:11Z)
• Potent but Stealthy: Rethink Profile Pollution against Sequential Recommendation via Bi-level Constrained Reinforcement Paradigm [44.622203626828345]
  Sequential Recommenders, which exploit dynamic user intents through interaction sequences, are vulnerable to adversarial attacks.<n>This paper focuses on the Profile Pollution Attack that subtly contaminates partial user interactions to induce targeted mispredictions.<n>We propose a constrained reinforcement driven attack CREAT that synergizes a bi-level optimization framework with multi-reward reinforcement learning to balance adversarial efficacy and stealthiness.
  arXiv  Detail & Related papers  (2025-11-12T15:00:52Z)
• Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction [51.50282796099369]
  This paper develops a multi-dimensional instruction uncertainty reduction framework to generate semantically constrained adversarial examples.<n>By predicting the language-guided sampling process, the optimization process will be stabilized by the designed ResAdv-DDIM sampler.<n>We realize the reference-free generation of semantically constrained 3D adversarial examples for the first time.
  arXiv  Detail & Related papers  (2025-10-27T04:02:52Z)
• Explicit Preference Optimization: No Need for an Implicit Reward Model [18.225409932618657]
  Direct preference optimization (DPO) and its offshoots circumvent the need for a separate reward training step.<n>We show that DPO-based objectives are nonetheless subject to sub-optimal regularization and counter-intuitive artifacts.
  arXiv  Detail & Related papers  (2025-06-09T07:11:01Z)
• DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing [58.62312400472865]
  Multi-modal face anti-spoofing (FAS) has emerged as a prominent research focus.<n>We propose a alignment module between modalities based on mutual information.<n>We employ a dual alignment optimization method that aligns both sub-domain hyperplanes and modality angle margins.
  arXiv  Detail & Related papers  (2025-03-01T10:12:00Z)
• Uncertainty-Penalized Direct Preference Optimization [52.387088396044206]
  We develop a pessimistic framework for DPO by introducing preference uncertainty penalization schemes. The penalization serves as a correction to the loss which attenuates the loss gradient for uncertain samples. We show improved overall performance compared to vanilla DPO, as well as better completions on prompts from high-uncertainty chosen/rejected responses.
  arXiv  Detail & Related papers  (2024-10-26T14:24:37Z)
• Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints [26.274786600234876]
  The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but amplify safety concerns. RLHF has emerged as a promising pathway towards AI alignment but brings forth challenges due to its complexity and dependence on a separate reward model. DPO has been proposed as an alternative, and it remains equivalent to RLHF under the reverse KL regularization constraint. We show that under certain $f$-divergences, including Jensen-Shannon divergence, forward KL divergences and $alpha$-divergences, the complex relationship between the reward and optimal policy can also be simplified
  arXiv  Detail & Related papers  (2023-09-28T08:29:44Z)
• AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning [24.028662731799127]
  We find that dropping attention positions with low attribution scores can accelerate training and increase the risk of overfitting. We develop a cross-tuning strategy to alternate fine-tuning and AD-DROP to avoid dropping high-attribution positions excessively.
  arXiv  Detail & Related papers  (2022-10-12T02:54:41Z)

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.