Qwen2.5-3B-Instruct Fine-tuned for AI Interview Feedback Generation
This is a LoRA (Low-Rank Adaptation) fine-tuned version of Qwen/Qwen2.5-3B-Instruct specifically optimized for generating constructive, actionable interview feedback. The model analyzes interview responses and provides detailed feedback on communication skills, technical accuracy, and areas for improvement.
Model Details
Base Model: Qwen/Qwen2.5-3B-Instruct
Fine-tuning Method: LoRA (Low-Rank Adaptation)
Training Data: 1,550 curated interview question-answer-feedback samples
1defgenerate_feedback(question, answer):2"""
3 Generate interview feedback for a given question-answer pair.
45 Args:
6 question (str): The interview question asked
7 answer (str): The candidate's response
89 Returns:
10 str: Generated feedback
11 """12 prompt =f"""Given the following interview question and candidate's answer, provide constructive feedback:
1314Question: {question}1516Answer: {answer}1718Feedback:"""1920 messages =[21{"role":"system","content":"You are an experienced interview coach providing constructive feedback."},22{"role":"user","content": prompt}23]2425 text = tokenizer.apply_chat_template(26 messages,27 tokenize=False,28 add_generation_prompt=True29)3031 inputs = tokenizer([text], return_tensors="pt").to(model.device)3233 outputs = model.generate(34**inputs,35 max_new_tokens=512,36 temperature=0.7,37 top_p=0.9,38 do_sample=True39)4041 response = tokenizer.decode(outputs[0], skip_special_tokens=True)4243# Extract only the feedback portion44 feedback = response.split("Feedback:")[-1].strip()4546return feedback
4748# Example usage49question ="Tell me about a time you handled a difficult team member."50answer ="I once worked with someone who didn't meet deadlines. I talked to them and helped them organize their work better."5152feedback = generate_feedback(question, answer)53print(feedback)
Example Output
Question: "What are your strengths and weaknesses?"
Candidate Answer: "My strength is that I work hard. My weakness is that I'm a perfectionist."
Generated Feedback:
Your response demonstrates self-awareness, which is positive. However, consider enhancing
your answer with specific examples. Instead of saying "I work hard," describe a situation
where your work ethic led to a successful outcome. For the weakness section, the
"perfectionist" answer is quite common - try to share a genuine area for improvement and,
importantly, explain the steps you're taking to address it. This shows growth mindset and
professional maturity. Also, quantify your achievements when possible to make your
strengths more tangible.
Training Details
Training Data
Dataset Size: 1,550 interview samples
Data Composition:
Technical interview questions and responses
Behavioral interview scenarios
HR screening questions
Role-specific questions across various industries
Feedback Quality: Each sample includes expert-crafted constructive feedback
Training Configuration
The model was fine-tuned using LoRA with the following approach:
Target Modules: Query and Value projection layers
Training Framework: PEFT (Parameter-Efficient Fine-Tuning)
Base Model: Qwen2.5-3B-Instruct
Optimization: Focused on maintaining base model capabilities while specializing in feedback generation
Evaluation
The model was evaluated using multiple methodologies:
Perplexity Measurement: Assessed language modeling quality
LLM-as-Judge Evaluation: Used advanced models to evaluate feedback quality
Human Evaluation: Domain experts reviewed generated feedback for:
Constructiveness
Actionability
Appropriateness
Helpfulness
Results demonstrated significant improvement in feedback quality compared to the base model, with particular strength in providing actionable suggestions and maintaining an encouraging tone.
Limitations
Language: Primarily optimized for English language interviews
Domain Coverage: Best performance on common interview scenarios; may be less effective for highly specialized technical domains
Context Window: Inherits the base model's context limitations
Cultural Context: Feedback style reflects professional standards common in Western business culture
Not a Replacement: Should be used as a supplementary tool, not a replacement for human career coaches or interview experts
Bias and Ethical Considerations
The model has been trained to provide constructive, unbiased feedback regardless of the content
Users should be aware that AI-generated feedback may not capture all nuances of human communication
This model should be used as a learning aid, and candidates should seek diverse perspectives
Feedback should be interpreted in the context of the specific role and industry
Model Architecture
This is a LoRA adapter that modifies the Qwen2.5-3B-Instruct base model. LoRA adds trainable rank decomposition matrices to specific layers while keeping the base model frozen, enabling efficient fine-tuning with minimal additional parameters.
Advantages of this approach:
Efficient training and inference
Preserves base model's general capabilities
Easy to share and deploy (only adapter weights needed)
Can be combined with other adapters
Citation
If you use this model in your research or application, please cite:
bibtex
1@misc{qwen2.5-3b-interview-feedback-lora,
2 author = {Charishma Tamarana},
3 title = {Qwen2.5-3B Fine-tuned for Interview Feedback Generation},
4 year = {2025},
5 publisher = {HuggingFace},
6 url = {https://huggingface.co/Charishma047/qwen2.5-3b-interview-feedback-lora}
7}
Also cite the base model:
bibtex
1@article{qwen2.5,
2 title={Qwen2.5: A Party of Foundation Models},
3 author={Qwen Team},
4 journal={arXiv preprint},
5 year={2024}
6}
Acknowledgments
Base Model: Qwen Team for the excellent Qwen2.5-3B-Instruct foundation model
Framework: HuggingFace for transformers and PEFT libraries
Training Infrastructure: Google Colab for providing accessible compute resources
