Skip to content
← Back to explorer

PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval

Chun Chet Ng, Jia Yu Lim, Wei Zeng Low · Nov 18, 2025 · Citations: 0

Automatic Metrics Coding Multi Agent
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Apr 6, 2026, 2:09 PM

Recent

Extraction refreshed

Apr 10, 2026, 7:20 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.55

Abstract

With the rapid progress of large language models (LLMs), financial information retrieval has become a critical industrial application. Extracting task-relevant information from lengthy financial filings is essential for both operational and analytical decision-making. We present PRISM, a training-free framework that integrates refined system prompting, in-context learning (ICL), and lightweight multi-agent coordination for document and chunk ranking tasks. Our primary contribution is a systematic empirical study of when each component provides value: prompt engineering delivers consistent performance with minimal overhead, ICL enhances reasoning for complex queries when applied selectively, and multi-agent systems show potential primarily with larger models and careful architectural design. Extensive ablation studies across FinAgentBench, FiQA-2018, and FinanceBench reveal that simpler configurations often outperform complex multi-agent pipelines, providing practical guidance for practitioners. Our best configuration achieves an NDCG@5 of 0.71818 on FinAgentBench, ranking third while being the only training-free approach in the top three. We provide comprehensive feasibility analyses covering latency, token usage, and cost trade-offs to support deployment decisions. The source code is released at https://bit.ly/prism-ailens.

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

Main weakness

No major weakness surfaced.

Trust level

Moderate

Eval-Fit Score

25/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Moderate

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: With the rapid progress of large language models (LLMs), financial information retrieval has become a critical industrial application.

Evaluation Modes

strong

Automatic Metrics

Confidence: Moderate Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: With the rapid progress of large language models (LLMs), financial information retrieval has become a critical industrial application.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: With the rapid progress of large language models (LLMs), financial information retrieval has become a critical industrial application.

Benchmarks / Datasets

strong

Finagentbench, Financebench

Confidence: Moderate Source: Persisted extraction evidenced

Useful for quick benchmark comparison.

Evidence snippet: Extensive ablation studies across FinAgentBench, FiQA-2018, and FinanceBench reveal that simpler configurations often outperform complex multi-agent pipelines, providing practical guidance for practitioners.

Reported Metrics

strong

Ndcg, Latency, Cost

Confidence: Moderate Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Our best configuration achieves an NDCG@5 of 0.71818 on FinAgentBench, ranking third while being the only training-free approach in the top three.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: With the rapid progress of large language models (LLMs), financial information retrieval has become a critical industrial application.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Ranking
  • Expertise required: Coding
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: Multi Agent
  • Quality controls: Not reported
  • Confidence: 0.55
  • Flags: ambiguous

Protocol And Measurement Signals

Benchmarks / Datasets

FinagentbenchFinancebench

Reported Metrics

ndcglatencycost

Research Brief

Deterministic synthesis

We present PRISM, a training-free framework that integrates refined system prompting, in-context learning (ICL), and lightweight multi-agent coordination for document and chunk ranking tasks. HFEPX signals include Automatic Metrics, Multi Agent with confidence 0.55. Updated from current HFEPX corpus.

Generated Apr 10, 2026, 7:20 AM · Grounded in abstract + metadata only

Key Takeaways

  • We present PRISM, a training-free framework that integrates refined system prompting, in-context learning (ICL), and lightweight multi-agent coordination for document and chunk…
  • Our primary contribution is a systematic empirical study of when each component provides value: prompt engineering delivers consistent performance with minimal overhead, ICL…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Cross-check benchmark overlap: Finagentbench, Financebench.
  • Validate metric comparability (ndcg, latency, cost).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Extraction confidence is probabilistic and should be validated for critical decisions.

Research Summary

Contribution Summary

  • We present PRISM, a training-free framework that integrates refined system prompting, in-context learning (ICL), and lightweight multi-agent coordination for document and chunk ranking tasks.
  • Our primary contribution is a systematic empirical study of when each component provides value: prompt engineering delivers consistent performance with minimal overhead, ICL enhances reasoning for complex queries when applied selectively,…
  • Extensive ablation studies across FinAgentBench, FiQA-2018, and FinanceBench reveal that simpler configurations often outperform complex multi-agent pipelines, providing practical guidance for practitioners.

Why It Matters For Eval

  • We present PRISM, a training-free framework that integrates refined system prompting, in-context learning (ICL), and lightweight multi-agent coordination for document and chunk ranking tasks.
  • Our primary contribution is a systematic empirical study of when each component provides value: prompt engineering delivers consistent performance with minimal overhead, ICL enhances reasoning for complex queries when applied selectively,…

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: Finagentbench, Financebench

  • Pass: Metric reporting is present

    Detected: ndcg, latency, cost

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote