LogicLens: Unified Forgery Analysis

• LogicLens is a unified framework for advanced text-centric forgery analysis that integrates visual and logical reasoning to detect and explain image manipulations.
• It employs a Cross-Cues-aware Chain of Thought mechanism and a weighted multi-task reinforcement learning strategy to optimize detection, region grounding, and explanation synthesis.
• The system is validated on the RealText benchmark using a PR² hierarchical pipeline, achieving state-of-the-art Macro-F1 scores in both fine-tuned and zero-shot settings.

LogicLens is a unified multimodal framework designed for advanced text-centric forgery analysis, integrating visual and logical reasoning within a single generative process. Developed to address the escalating sophistication of text-centric image manipulations enabled by generative AI, LogicLens jointly optimizes detection of forgeries, region grounding, and explanation synthesis. The architecture is distinguished by its Cross-Cues-aware Chain of Thought (CCT) mechanism for deep visual-logical co-reasoning, a weighted multi-task reward system for reinforcement alignment, and the hierarchical PR² annotation pipeline, validated on the large-scale RealText benchmark (Zeng et al., 25 Dec 2025).

1. Joint Problem Formulation

LogicLens reframes text-centric forgery analysis as a joint generative task over an image $I$ and prompt $T$, producing a structured report $R = (c, B, E)$, where $c$ is the authenticity verdict, $B$ localizes forged regions, and $E$ is a natural-language rationale. Model parameters $\theta$ are learned by maximizing the expected log-likelihood:

$$\hat \theta = \arg\max_\theta \; \mathbb{E}_{(I,T,R)\sim \mathcal D}\bigl[\log P_\theta(R \mid I,T)\bigr],$$

where $R$ is generated token-wise in an autoregressive fashion. Evaluation aggregates detection $F_1$, grounding mean F1 ($T$0), and explanation semantic similarity into Macro-F1 ($T$1):

$T$2

This joint paradigm contrasts with prior decoupled approaches and is foundational for LogicLens’s unified reasoning capabilities (Zeng et al., 25 Dec 2025).

2. PR² Hierarchical Data-Curation Pipeline

To enable high-fidelity supervision, LogicLens employs the PR² pipeline—a multi-agent system comprising Perceiver, Reasoner, and Reviewer—prior to training:

• Perceiver ingests raw images, fused RGB-mask visualizations, and OCR transcripts, yielding preliminary forensic analyses: anomalies, bounding boxes, and draft rationales.
• Reasoner structures these drafts into a six-stage CCT outline, evaluating format, logic, and grounding accuracy, producing a scalar quality score.
• Reviewer applies QA, iteratively requesting corrections or enhancements until a quality threshold is met.

This pipeline ensures cognitively-aligned, fully-annotated samples, encoded as $T$3 triples for model fine-tuning and policy-gradient rewards (Zeng et al., 25 Dec 2025).

3. Cross-Cues-aware Chain of Thought (CCT) Reasoning

CCT is the deep reasoning core of LogicLens, structured in six interdependent stages with chain states $T$4:

1. Knowledge Preparation: Aggregates image context, OCR tokens $T$5, and relevant forensic/semantic triggers.
2. Visual Cue Extraction: Computes global ($T$6) and local ($T$7) anomaly cues via vision backbones, aggregated into $T$8.
3. Logical Cue Extraction: Processes symbolic logical cues $T$9 from OCR, checking arithmetic and contextual consistency, updating $R = (c, B, E)$0.
4. Cross-Cue Validation & Filtering: Applies a learned salience scorer $R = (c, B, E)$1 over visual and logical cues, selecting high-value elements for $R = (c, B, E)$2.
5. Grounding: Matches selected cues to OCR tokens and regions, constructing the tampered region set $R = (c, B, E)$3 and updating $R = (c, B, E)$4.
6. Report Synthesis: Decides verdict $R = (c, B, E)$5 and synthesizes rationale $R = (c, B, E)$6 for token-wise report generation.

At each step, modalities are aggregated as:

$R = (c, B, E)$7

where $R = (c, B, E)$8 is the stage-specific modality extractor. CCT enables robust cross-validation between observed visual evidence and logical structure, critical for precise forgery identification (Zeng et al., 25 Dec 2025).

4. Weighted Multi-Task Reinforcement Alignment

After supervised pretraining, LogicLens applies GRPO-based reinforcement learning using a composite, weighted multi-task reward:

$R = (c, B, E)$9

with empirically set weights $c$0.

• $c$1: Presence of structural tags in output.
• $c$2: Sum of detection, region count, and IoU-based rewards; e.g., for mIoU $c$3, $c$4.
• $c$5: Cosine similarity of explanation sentence embeddings.

Policy-gradient actor–critic optimization maximizes expected $c$6, with a learned value baseline $c$7 for variance reduction:

$c$9

This reward structure tightly couples detection, grounding, and explanation, enhancing holistic model performance (Zeng et al., 25 Dec 2025).

5. RealText Benchmark Dataset

LogicLens’s supervised and RL training leverages RealText, a dataset produced via the PR² pipeline starting from ~50K candidate images filtered with GPT-4o and DINOv2. The final RealText dataset comprises 5,397 images with:

• authenticity labels $c$8
• pixel-level bounding boxes for all tampered text regions
• free-form explanations identifying both visual and logical anomalies

Forged images include copy-move, AIGC inpainting, text replacement, logo swapping, and arithmetic/date tampering, with a “dense-text” subset (≥ 10 text-lines, 905 images). RealText establishes the first unified and large-scale multi-task benchmark for text-centric forensic analysis, surpassing the scope and granularity of T-IC13 and T-SROIE (Zeng et al., 25 Dec 2025).

6. Experimental Evaluation and Comparative Results

LogicLens is evaluated on RealText (fine-tuned), T-IC13 (zero-shot), and T-SROIE (zero-shot dense). Macro-F1 is the principal aggregate metric.

Dataset	Detection F₁	Grounding mF₁	Explanation BS-F₁	Macro-F₁
RealText (FT)	93.2	36.7	76.9	68.9
T-IC13 (ZS)	93.2	67.6	78.5	79.8
T-SROIE (ZS, dense)	99.4	11.0	77.0	62.5
FakeShield	—	—	—	40.6
GPT-4o	—	—	—	55.8
Gemini-2.5-Pro	—	—	—	53.9
InternVL-3.5	—	—	—	48.8
Qwen2.5-VL (SFT)	—	—	—	36.3

LogicLens demonstrates clear superiority in joint reasoning and grounding, with strong zero-shot generalization to unseen datasets (Zeng et al., 25 Dec 2025).

7. Strengths, Limitations, and Prospects

LogicLens advances text-centric forgery analysis via generative integration of detection, grounding, and explanation, deep co-reasoning through CCT, reward-aligned RL, and benchmarking with RealText. Principal strengths include state-of-the-art Macro-F1 performance, interpretable and structured output, and adaptability to forensic workflows.

Limitations include dependency on OCR quality and world-knowledge recall, the necessity of precise reward tuning, and inference cost due to model scale (~7B parameters). Future work aims to implement end-to-end OCR and vision backbones, extend modality coverage (e.g., video, multi-frame consistency), reinforce adversarial robustness, and enable efficient distillation for edge deployment (Zeng et al., 25 Dec 2025).

In aggregate, LogicLens establishes a comprehensive paradigm for visual-logical co-reasoning in text-centric forgery analysis, unifying multiple subtasks under a reinforcement-aligned multimodal architecture, anchored by a cognitively-validated, large-scale annotated benchmark.