Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Grammarly Launches 8 AI Writing Tools: Citation Finder, AI Grader, Plagiarism Checker, Proofreader and More

LegalZoom To Offer Patent Filings Via Own Law Firm – Artificial Lawyer

Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence – Takara TLDR

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Business AI
    • Advanced AI News Features
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Hugging Face

Paper page – TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

By Advanced AI EditorAugust 2, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


TARS, a token-adaptive preference strategy, improves multimodal large language models by reducing hallucinations through min-max optimization under semantic constraints.

Multimodal large language models (MLLMs) enable vision-language reasoning,
yet often generate plausible outputs that are factually incorrect or visually
ungrounded, thereby compromising their reliability. Direct preference
optimization (DPO) is a common strategy for correcting hallucinations by
aligning model outputs with human preferences. Existing DPO strategies
typically treat hallucination-related preferences as fixed targets, relying on
static supervision signals during training. This approach tends to overfit to
superficial linguistic cues in preference data, leading to distributional
rigidity and spurious correlations that impair grounding in causally relevant
visual information. To overcome this limitation, we propose TARS, a
token-adaptive preference strategy that reformulates DPO as a min-max
optimization problem. TARS maximizes token-level distributional shifts under
semantic constraints to simulate alignment uncertainty, and simultaneously
minimizes the expected preference loss under these controlled perturbations.
This joint objective preserves causal grounding while mitigating overfitting to
preference patterns, thereby reducing hallucinations in multimodal reasoning.
We evaluate TARS on multiple hallucination benchmarks and find consistently
strong performance. Using only 4.8k preference samples and no expert feedback,
TARS reduces hallucination rates from 26.4% to 13.2% and decreases cognition
value from 2.5 to 0.4. It outperforms standard DPO and matches GPT-4o on
several key metrics.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleDeepSeek hired talent from Microsoft’s controversial AI research lab in China
Next Article Tesla to appeal jury verdict that held it partially liable for fatal crash
Advanced AI Editor
  • Website

Related Posts

Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence – Takara TLDR

August 20, 2025

Leveraging Large Language Models for Predictive Analysis of Human Misery – Takara TLDR

August 20, 2025

Next Visual Granularity Generation – Takara TLDR

August 20, 2025

Comments are closed.

Latest Posts

Barbara Hepworth Sculpture Will Remain in UK After £3.8 M. Raised

After 12-Year Hiatus, Egypt’s Alexandria Biennale Will Return

Ai Weiwei Visits Ukraine’s Front Line Ahead of Kyiv Installation

Maren Hassinger to Receive Her Largest Retrospective to Date Next Year

Latest Posts

Grammarly Launches 8 AI Writing Tools: Citation Finder, AI Grader, Plagiarism Checker, Proofreader and More

August 20, 2025

LegalZoom To Offer Patent Filings Via Own Law Firm – Artificial Lawyer

August 20, 2025

Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence – Takara TLDR

August 20, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • Grammarly Launches 8 AI Writing Tools: Citation Finder, AI Grader, Plagiarism Checker, Proofreader and More
  • LegalZoom To Offer Patent Filings Via Own Law Firm – Artificial Lawyer
  • Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence – Takara TLDR
  • DeepSeek’s V3.1 update and missing R1 label spark speculation over fate of R2 AI model
  • How Claude Code AI Handles 1 Million Tokens to Boost Efficiency

Recent Comments

  1. Richardsmeap on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  2. JimmieSed on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  3. kinobay-346 on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  4. Febilycit on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  5. Felixtip on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.