Skip to content
← Back to explorer

SarcasmMiner: A Dual-Track Post-Training Framework for Robust Audio-Visual Sarcasm Reasoning

Zhu Li, Yongjian Chen, Huiyuan Lai, Xiyuan Gao, Shekhar Nayak, Matt Coler · Mar 5, 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

Mar 5, 2026, 3:22 PM

Recent

Extraction refreshed

Mar 7, 2026, 5:25 PM

Fresh

Extraction source

Runtime deterministic fallback

Confidence 0.35

Abstract

Multimodal sarcasm detection requires resolving pragmatic incongruity across textual, acoustic, and visual cues through cross-modal reasoning. To enable robust sarcasm reasoning with foundation models, we propose SarcasmMiner, a reinforcement learning based post-training framework that resists hallucination in multimodal reasoning. We reformulate sarcasm detection as structured reasoning and adopt a dual-track distillation strategy: high-quality teacher trajectories initialize the student model, while the full set of trajectories trains a generative reward model (GenRM) to evaluate reasoning quality. The student is optimized with group relative policy optimization (GRPO) using decoupled rewards for accuracy and reasoning quality. On MUStARD++, SarcasmMiner increases F1 from 59.83% (zero-shot), 68.23% (supervised finetuning) to 70.22%. These findings suggest that reasoning-aware reward modeling enhances both performance and multimodal grounding.

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 0.35 (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 secondary eval reference to pair with stronger protocol papers.

Main weakness

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

Trust level

Low

Eval-Fit Score

0/100 • 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: Runtime deterministic fallback missing

No explicit feedback protocol extracted.

Evidence snippet: Multimodal sarcasm detection requires resolving pragmatic incongruity across textual, acoustic, and visual cues through cross-modal reasoning.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Runtime deterministic fallback evidenced

Includes extracted eval setup.

Evidence snippet: Multimodal sarcasm detection requires resolving pragmatic incongruity across textual, acoustic, and visual cues through cross-modal reasoning.

Quality Controls

missing

Not reported

Confidence: Low Source: Runtime deterministic fallback missing

No explicit QC controls found.

Evidence snippet: Multimodal sarcasm detection requires resolving pragmatic incongruity across textual, acoustic, and visual cues through cross-modal reasoning.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Runtime deterministic fallback missing

No benchmark anchors detected.

Evidence snippet: Multimodal sarcasm detection requires resolving pragmatic incongruity across textual, acoustic, and visual cues through cross-modal reasoning.

Reported Metrics

partial

Accuracy, F1

Confidence: Low Source: Runtime deterministic fallback evidenced

Useful for evaluation criteria comparison.

Evidence snippet: The student is optimized with group relative policy optimization (GRPO) using decoupled rewards for accuracy and reasoning quality.

Rater Population

missing

Unknown

Confidence: Low Source: Runtime deterministic fallback missing

Rater source not explicitly reported.

Evidence snippet: Multimodal sarcasm detection requires resolving pragmatic incongruity across textual, acoustic, and visual cues through cross-modal reasoning.

Human Data Lens

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

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.35
  • Flags: low_signal, possible_false_positive, runtime_fallback_extraction

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

accuracyf1

Research Brief

Deterministic synthesis

To enable robust sarcasm reasoning with foundation models, we propose SarcasmMiner, a reinforcement learning based post-training framework that resists hallucination in multimodal reasoning. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 7, 2026, 5:25 PM · Grounded in abstract + metadata only

Key Takeaways

  • To enable robust sarcasm reasoning with foundation models, we propose SarcasmMiner, a reinforcement learning based post-training framework that resists hallucination in multimodal…
  • The student is optimized with group relative policy optimization (GRPO) using decoupled rewards for accuracy and reasoning quality.
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (accuracy, f1).

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

  • To enable robust sarcasm reasoning with foundation models, we propose SarcasmMiner, a reinforcement learning based post-training framework that resists hallucination in multimodal reasoning.
  • The student is optimized with group relative policy optimization (GRPO) using decoupled rewards for accuracy and reasoning quality.
  • On MUStARD++, SarcasmMiner increases F1 from 59.83% (zero-shot), 68.23% (supervised finetuning) to 70.22%.

Why It Matters For Eval

  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

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.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: accuracy, f1

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