Skip to content
← Back to explorer

DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs

Nayoung Choi, Jonathan Zhang, Jinho D. Choi · Jan 12, 2026 · Citations: 0

Automatic Metrics
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 8, 2026, 10:34 PM

Recent

Extraction refreshed

Apr 13, 2026, 6:37 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.45

Abstract

Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts. While recent LLMs support extended context windows, efficient management of dialogue history in practice is needed due to inference cost and latency constraints. We present DyCP, a lightweight context management method implemented outside the LLM that dynamically identifies and retrieves relevant dialogue segments conditioned on the current turn, without offline memory construction. DyCP manages dialogue context while preserving the sequential nature of dialogue without predefined topic boundaries, enabling adaptive and efficient context selection. Across three long-form dialogue benchmarks-LoCoMo, MT-Bench+, and SCM4LLMs-and multiple LLM backends, DyCP achieves competitive answer quality in downstream generation, with more selective context usage and improved inference efficiency.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.45 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

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

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

5/100 • 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: Low

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: Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts.

Benchmarks / Datasets

partial

MT Bench

Confidence: Low Source: Persisted extraction evidenced

Useful for quick benchmark comparison.

Evidence snippet: Across three long-form dialogue benchmarks-LoCoMo, MT-Bench+, and SCM4LLMs-and multiple LLM backends, DyCP achieves competitive answer quality in downstream generation, with more selective context usage and improved inference efficiency.

Reported Metrics

partial

Latency, Cost, Inference cost

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: While recent LLMs support extended context windows, efficient management of dialogue history in practice is needed due to inference cost and latency constraints.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts.

Human Data Lens

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

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.45
  • Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

MT-Bench

Reported Metrics

latencycostinference cost

Research Brief

Deterministic synthesis

We present DyCP, a lightweight context management method implemented outside the LLM that dynamically identifies and retrieves relevant dialogue segments conditioned on the current turn, without offline memory construction. HFEPX signals include Automatic Metrics with confidence 0.45. Updated from current HFEPX corpus.

Generated Apr 13, 2026, 6:37 AM · Grounded in abstract + metadata only

Key Takeaways

  • We present DyCP, a lightweight context management method implemented outside the LLM that dynamically identifies and retrieves relevant dialogue segments conditioned on the current…
  • Across three long-form dialogue benchmarks-LoCoMo, MT-Bench+, and SCM4LLMs-and multiple LLM backends, DyCP achieves competitive answer quality in downstream generation, with more…

Researcher Actions

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

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • We present DyCP, a lightweight context management method implemented outside the LLM that dynamically identifies and retrieves relevant dialogue segments conditioned on the current turn, without offline memory construction.
  • Across three long-form dialogue benchmarks-LoCoMo, MT-Bench+, and SCM4LLMs-and multiple LLM backends, DyCP achieves competitive answer quality in downstream generation, with more selective context usage and improved inference efficiency.

Why It Matters For Eval

  • Across three long-form dialogue benchmarks-LoCoMo, MT-Bench+, and SCM4LLMs-and multiple LLM backends, DyCP achieves competitive answer quality in downstream generation, with more selective context usage and improved inference efficiency.

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: MT-Bench

  • Pass: Metric reporting is present

    Detected: latency, cost, inference cost

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

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

Post a Job Get a Quote