Skip to content

Tutorial / Demo · Jupyter Notebook

LLM_sycophancy_dpo

What it is

This repository provides tools to evaluate and demonstrate a Qwen2.5-1.5B model fine-tuned with DPO to reduce sycophancy, including baseline and post-training evaluation notebooks, a dataset cleaning script, and a Gradio app for interactive comparison.

Scored at16e323515 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Distribution based on AI work

1 / 2
NLP & LLMs: 47.4%Machine Learning: 36.8%Data Science: 15.8%
  • NLP & LLMs47%
  • Machine Learning37%
  • Data Science16%

Each field's share of the project's AI work, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths3

  • Provides a clear demonstration of sycophancy reduction via DPO fine-tuning
  • Includes evaluation code for standard sycophancy benchmarks (SycoBench)
  • Offers an interactive Gradio app for comparing model behaviors

Limitations

The owner keeps this project's limitations private.

Around it on the NLP & LLMs board

Whole board
  1. 176codelab-ai-genkit-ragTutorial / Demo · TypeScript33.6/100ExplorationSai Kannadkar
  2. 177viewerTutorial / Demo · Dockerfile32.5/100ExplorationPetr Sovadina
  3. 178LLM_sycophancy_dpoTutorial / Demo · Jupyter Notebook32.3/100ExplorationKashish gupta
  4. 179HINDI-LIWCEducational Implementation · Python31.9/100ExplorationTanay kumar
  5. 180EDUGENIE-AIML Application · Python31.8/100ExplorationKashish gupta

More from Kashish gupta