Hierarchical Summarization

What Is Hierarchical Summarization?

When to Use Hierarchical Summarization

Document Tree Structure

from dataclasses import dataclass, field
from typing import List, Optional

@dataclass
class DocNode:
    title: str
    content: str = ''
    summary: str = ''
    children: List['DocNode'] = field(default_factory=list)

# Example: book with 3 chapters, each with 3 sections
book = DocNode(
    title='My Book',
    children=[
        DocNode('Chapter 1', children=[
            DocNode('Section 1.1', content='...raw text...'),
            DocNode('Section 1.2', content='...raw text...'),
        ]),
        DocNode('Chapter 2', children=[
            DocNode('Section 2.1', content='...raw text...'),
        ])
    ]
)

Bottom-Up Summarization

import openai
client = openai.OpenAI(api_key='sk-...')

def summarize_text(text, role='section'):
    resp = client.chat.completions.create(
        model='gpt-4o',
        messages=[
            {'role': 'system',
             'content': f'Summarize this {role} in 3-5 sentences.'},
            {'role': 'user', 'content': text}
        ]
    )
    return resp.choices[0].message.content

def summarize_tree(node, depth=0):
    role = ['document', 'chapter', 'section', 'page'][min(depth, 3)]
    if not node.children:
        node.summary = summarize_text(node.content, role)
    else:
        for child in node.children:
            summarize_tree(child, depth + 1)
        combined = '\n\n'.join(
            f'{c.title}:\n{c.summary}' for c in node.children
        )
        node.summary = summarize_text(combined, role)
    return node.summary

Progressive Compression

PAGE_PROMPT = 'Summarize this page in 2-3 sentences (under 80 words).'
SECTION_PROMPT = 'Given these page summaries, write a section summary in 3-4 sentences (under 120 words).'
CHAPTER_PROMPT = 'Given these section summaries, write a chapter summary in 4-5 sentences (under 150 words).'
DOC_PROMPT = 'Given these chapter summaries, write an executive summary of the entire document (under 200 words).'

Maintaining Coherence Across Levels

def summarize_sections_for_chapter(chapter_title, section_summaries):
    content = '\n\n'.join(
        f'Section: {s["title"]}\n{s["summary"]}'
        for s in section_summaries
    )
    prompt = (
        f'Chapter: {chapter_title}\n\n'
        'Below are summaries of each section. '
        'Write a unified chapter summary without repeating '
        'the same facts from multiple sections.\n\n' + content
    )
    resp = client.chat.completions.create(
        model='gpt-4o',
        messages=[{'role': 'user', 'content': prompt}]
    )
    return resp.choices[0].message.content

Research Paper Hierarchy

SECTION_PROMPTS = {
    'abstract': 'Summarize the paper abstract: what problem, method, and result?',
    'introduction': 'Summarize the introduction: what gap does the paper address?',
    'methods': 'Summarize the methods: what approach was used?',
    'results': 'Summarize the results: what were the key findings and metrics?',
    'discussion': 'Summarize the discussion: what do the results mean?',
    'conclusion': 'Summarize the conclusion and future work.'
}

def summarize_paper(sections_dict):
    section_summaries = {}
    for section, text in sections_dict.items():
        prompt = SECTION_PROMPTS.get(section, 'Summarize this section.')
        section_summaries[section] = call_llm(prompt, text)
    return section_summaries

Legal Contract Hierarchy

LEGAL_PROMPT = '''Summarize this contract clause in plain English.
Preserve: all monetary amounts, dates, party names, and conditionals.
Flag any obligation with [OBLIGATION] and any amount with [AMOUNT].'''

def summarize_clause(clause_text):
    resp = client.chat.completions.create(
        model='gpt-4o',
        messages=[
            {'role': 'system', 'content': LEGAL_PROMPT},
            {'role': 'user', 'content': clause_text}
        ]
    )
    return resp.choices[0].message.content

Storing Hierarchical Summaries

import json

def tree_to_dict(node):
    return {
        'title': node.title,
        'summary': node.summary,
        'children': [tree_to_dict(c) for c in node.children]
    }

def save_tree(node, path):
    with open(path, 'w') as f:
        json.dump(tree_to_dict(node), f, indent=2)
    print(f'Saved summary tree to {path}')

Incremental Updates

def update_node(node, updated_child_title):
    # Re-summarize the changed child
    for child in node.children:
        if child.title == updated_child_title:
            summarize_tree(child)  # re-summarize from leaves
            break
    # Re-summarize current node from updated children
    combined = '\n\n'.join(
        f'{c.title}:\n{c.summary}' for c in node.children
    )
    node.summary = summarize_text(combined)
    return node.summary

Comparing Flat vs Hierarchical

Knowledge Check

Recap: Hierarchical Summarization