Summllama3 70B

🚀 SummLlama3-70B

Are you in search of a summarizer capable of generating more human-preferred summaries across diverse domains? Our SummLlama3-70B might be the exact solution you need! SummLlama3-70B is initialized from Llama3-70B-Instruct and undergoes additional training using Direct Preference Optimization (DPO) based on large-scale (over 100K) summarization feedback.

🚀 Quick Start

Key Information

Model Links

• SummLlama3-70B
  • https://huggingface.co/DISLab/SummLlama3-8B
  • https://huggingface.co/DISLab/SummLlama3-70B
• SummLlama3.1-Series
  • https://huggingface.co/DISLab/SummLlama3.1-8B
  • https://huggingface.co/DISLab/SummLlama3.1-70B
• SummLlama3.2-Series
  • https://huggingface.co/DISLab/SummLlama3.2-3B

Recommended Prompt for Text Summarization

We recommend using the following prompt to obtain summaries, as the model was trained with it.

def format_chat_template(document):
    instruction = "Please summarize the input documnet."
    row_json = [{"role": "user", "content": f"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Input:\n{document}\n\n### Response:\n"}]
    return tokenizer.apply_chat_template(row_json, tokenize=False)

✨ Features

• Diverse Feedback Sources: The feedback used for training encompasses a wide range of input documents, from short to lengthy texts, including both dialogue and non-dialogue formats, and spans across seven distinct domains:
  • Four non-dialogue domains: News, Lifestyle, Report, Medical
  • Three dialogue domains: Daily Life, Interview, Meeting
• Outstanding Performance: This model excels in faithfulness, completeness, and conciseness, which are the three key aspects for human-preferred summarization.
  • Faithfulness: It does not manipulate the information in the input text and avoids adding any information not directly inferable from the input text.
  • Completeness: It ensures the inclusion of all key information from the input text in the output summary.
  • Conciseness: It refrains from incorporating information outside the key information in the output, maintaining a succinct and focused summary.

📚 Documentation

Evaluation Results

Automated Evaluation

Human Evaluation

Automated Evaluation using FineSurE

Example

See an example of how the summary improved by SummLlama3-8B over Llama3-8/70B-Instruct on the following document:

The summary of SummLlama3-8B can be considered a much human-preferred summary for the following reasons:

• Core Focus: The summary accurately captures the main theme of the conversation, which revolves around the Thanksgiving dinner arrangements. It highlights how the two people confirm plans, discuss what to bring, and finalize the decision for Person2 to bring wine instead of pie. This maintains the core context.
• Inclusion of Key-facts: The summary covers the important details of the conversation, including Person2's initial offer to bring dessert (pumpkin pie) and the shift to bringing wine due to another family member handling dessert. Other summaries tend to overlook or simplify this progression, while SummLlama3-8B fully captures the interaction’s key events.
• Clarity and Conciseness: The summary is structured in a straightforward, concise manner, effectively summarizing the conversation without unnecessary details. It presents the flow and outcome of the discussion clearly, making it easy for readers to understand. The logical order of events is maintained, ensuring a smooth narrative.
• Accurate Role Depiction: The summary clearly identifies Person1 as the host and Paul (Person2) as the guest, which helps clarify their relationship and the nature of the conversation. This distinction is more explicit in SummLlama3-8B compared to other summaries, which might leave these roles more ambiguous.

Paper Reference

Please refer to our paper to learn how to exploit LLM-generated feedback in the context of text summarization.