Skip to content

Latest commit

Β 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
Β 
Β 
Β 
Β 

Repository files navigation

Enterprise RAG & LLM Evaluation: Corporate Intelligence Benchmark

An empirical evaluation study and architectural specification analyzing Retrieval-Augmented Generation (RAG) failure modes, prompt engineering constraints, and document retrieval strategies across 160+ enterprise SEC filings (10-Ks, 10-Qs, 8-Ks) and earnings transcripts.


πŸ“Œ Executive Summary

Enterprise competitive intelligence requires precise, fact-grounded synthesis from hundreds of pages of unstructured financial and strategic disclosures. This project evaluates an internal Natural Language Processing (NLP) / Large Language Model (LLM) chatbot designed for Ball Corporation to track strategic customer performance (specifically Molson Coors).

Core Findings & Metrics

  • Baseline Retrieval Accuracy: The system achieved a 63% baseline factual accuracy rate across complex multi-document financial queries.
  • Order-of-Operations Bias: Uncovered that the LLM processes prompt structural constraints sequentially rather than holistically (e.g., placing format constraints at the beginning of the prompt resolved paragraph-count truncation errors).
  • Retrieval Bottlenecks Identified: Uncovered primary RAG degradation points including sequential retrieval bias, context-window saturation (capping citations at 3 documents), and cross-entity pollution.

πŸ”¬ Empirical Failure Modes Analyzed

Failure Mode Root Cause in RAG Pipeline Observed Impact
Sequential Retrieval Bias Naive top-$k$ similarity search without temporal re-ranking The model cited the first available document rather than the most recent/authoritative filing.
Citation Truncation Rigid context chunk retrieval limits LLM capped retrieval at 3 documents, failing to aggregate data across multi-year trends.
Cross-Entity Confusion Lack of named-entity recognition (NER) pre-filtering Trigger words (e.g., "marketing campaign") retrieved unrelated competitor filings (e.g., Coca-Cola).
Prompt Instruction Decay End-of-prompt constraint placement Format instructions placed at the end of long prompts were ignored; front-loading constraints restored compliance.

πŸ› οΈ Architectural Recommendations & System Fixes

To resolve the 37% error margin, the report outlined four targeted technical enhancements:

  1. Hierarchical Document Indexing: Implement a two-tier retrieval architecture (searching document-level metadata/titles before content chunks) to prevent irrelevant section scanning.
  2. Temporal & Metadata Re-Ranking: Apply recency-weighted re-ranking algorithms so newer quarterly earnings and 8-K filings override older disclosures.
  3. Chain-of-Thought (CoT) Verification: Enforce step-by-step verification prompts ("think twice", self-correction queries) to reduce hallucinated financial ratios.
  4. Automated Evaluation Framework: Transition from manual ad-hoc testing to a systematic evaluation benchmark scoring factual recall, faithfulness, and hallucination rate.

πŸ“‚ Repository Contents

  • reports/: Complete technical whitepaper and business case analysis.
  • evaluation_data/: Empirical prompt-response benchmark logs tracking query accuracy, model responses, and error categories.

About

Empirical evaluation study and architectural failure-mode analysis for enterprise Retrieval-Augmented Generation (RAG) across SEC filings.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors