Don’t Corrupt the Fact: A Trustworthy RAG Watermarking Framework based on Dual Factual Shield (2026.acl-long)
Copied to clipboard
| Challenge: | Existing watermarking methods are fact-agnostic and cause "faithfulness hallucinations" a novel framework to enforce knowledge loyalty is proposed to improve watermarks . |
| Approach: | They propose a new framework that enforces knowledge loyalty by spoofing terms from retrieved contexts and prompt-based semantic guidance to protect against factual corruption. |
| Outcome: | The proposed framework reduces the Knowledge Corruption Rate while maintaining its original high security and robustness. |
Similar Papers
Knowledge-Infused Multi-Bit Watermarking for RAG Knowledge Bases (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing RAG watermarking methods are limited in their encoding capacity and potential degradation of performance or knowledge quality. |
| Approach: | They propose knowledge-infused and multi-bit watermarking (KMW) for RAG knowledge bases by benign knowledge completion and a tailored generative watermark algorithm. |
| Outcome: | The proposed method extracts watermarks from adversarial RAGs while remaining stealthy and secure. |
Mask-to-Correct+: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fact correction ignore semantic faithfulness in their process. |
| Approach: | They propose a supervised learning approach that uses a diversity-aware masking approach to identify erroneous spans of claims and evaluate the faithfulness of corrections using retrieved evidence. |
| Outcome: | The proposed framework outperforms baseline frameworks on social media datasets, achieving up to 14% improvement in SARI scores, without using gold evidence. |
S-RAG: A Novel Audit Framework for Detecting Unauthorized Use of Personal Data in RAG Systems (2025.acl-long)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) systems rely on external data for accurate and context-specific responses. |
| Approach: | They propose a framework that enables users to determine whether their textual data has been utilized in RAG systems even in black-box settings with no prior system knowledge. |
| Outcome: | The proposed framework achieves an improvement in Accuracy by 19.9% while maintaining strong performance under adversarial defenses. |
Integrity Shield A System for Ethical AI Use & Authorship Transparency in Assessments (2026.eacl-demo)
Copied to clipboard
| Challenge: | Existing methods for detecting authorship and short answers are ineffective when students query proprietary black-box systems using instructor-provided documents. |
| Approach: | They propose a document-layer watermarking system that embeds schema-aware, item-level watermarks into assessment PDFs while keeping their human-visible appearance unchanged. |
| Outcome: | The proposed system achieves high prevention and detection reliability across 30 question papers spanning STEM, humanities, and medical reasoning. |
FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing faithful RAG approaches enforce strict context adherence, but they forcibly suppress the model’s parametric knowledge, which undermines the model's internal knowledge structure and increases the risk of misinterpreting the context. |
| Approach: | They propose a framework that resolves knowledge conflicts by explicitly modeling discrepancies between the model’s parametric knowledge and retrieved context. |
| Outcome: | The proposed framework outperforms state-of-the-art methods in knowledge conflict cases and identifies conflicting knowledge at the fact level and designs a self-thinking process. |
Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for fact checking RAG outputs rely on large language models. |
| Approach: | They propose a method that computes a factuality score that can be thresholded to yield a binary decision to check RAG outputs. |
| Outcome: | The proposed method is low latency and low cost at run-time and no need for LLM fine-tuning. |
Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge (2025.findings-acl)
Copied to clipboard
| Challenge: | Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. |
| Approach: | They propose a data watermarking approach that injects coherent and plausible yet fictitious knowledge into training data using generated passages describing a fictious entity and its associated attributes. |
| Outcome: | The proposed method is designed to be memorized by the LLM, and that increasing their density, length, and diversity of attributes strengthens their memorization. |
Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding (2026.findings-acl)
Copied to clipboard
Weixu Zhang, Fanghua Ye, Qiang Gao, Jian Li, Haolun Wu, Yuxing Tian, Sijing Duan, Nan Du, Xiaolong Li
| Challenge: | Large language models produce content that contradicts or overlooks information provided in the input context, a phenomenon known as faithfulness hallucination. |
| Approach: | They propose a lightweight framework that boosts the generation probability of context-relevant tokens by boosting the generation of tokens. |
| Outcome: | The proposed framework improves faithfulness metrics with minimal generation overhead. |
Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches to attack large language models rely heavily on retrieval and generation stages, limiting their effectiveness in black-box scenarios. |
| Approach: | They propose a retrieval-augmented generation framework that leverages a white-box LLM as an attacker to generate and iteratively optimize malicious passages at the token level. |
| Outcome: | The proposed framework outperforms existing approaches in retrieval-stage and end-to-end attacks on black-box RAG systems. |
Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks focus on detection-quality tradeoffs and overlook factual risks. |
| Approach: | They propose a method that assesses factual accuracy and coherence . they use a factor-weighted score to prioritize factual accurate beyond coherency . |
| Outcome: | The proposed method assesses factual accuracy and coherence in medical text . it shows current watermarking methods substantially compromise medical factuality . |