Guaranteeing Faithful Evidence Extraction in Speculative Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2609.10046v2
• Date: Fri, 11 Sep 2026 14:57:49 GMT
• Title: Guaranteeing Faithful Evidence Extraction in Speculative Retrieval-Augmented Generation
• Abstract summary: We introduce Constrained Hybrid Decoding (CHyD), a novel faithfulness-first paradigm for speculative RAG.<n>Our approach enforces hard decoding constraints that restrict generation to continuous spans present in the retrieved documents.<n>Results show that existing hybrid methods frequently hallucinate quoted spans, with exact extraction accuracy dropping below 40% in technical domains.
• Score: 1.002229589104305
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are increasingly used as interfaces for information retrieval, but they remain prone to hallucinations and faithfulness errors, in which the generated answers diverge from the retrieved evidence. While Retrieval-Augmented Generation (RAG) and recent hybrid or semi-extractive approaches mitigate this issue, they do not guarantee that quoted or extracted spans are verbatim from the retrieved context. This limitation can have severe consequences in safety-critical domains, where answers must exactly match certified documentation. We introduce Constrained Hybrid Decoding (CHyD), a novel faithfulness-first paradigm for speculative RAG. While traditional speculative decoding is optimized for inference speed, CHyD repurposes this architecture to ensure faithful verbatim evidence extraction when the extraction mode is correctly triggered. Our approach enforces hard decoding constraints that restrict generation to continuous spans present in the retrieved documents. This design provides a robust but straightforward guarantee: any explicitly quoted span in the output appears verbatim in the provided context. We evaluate our method across state-of-the-art LLMs on diverse abstractive, extractive, and semi-extractive QA benchmarks, including technical datasets motivated by aircraft maintenance. Results show that existing hybrid methods frequently hallucinate quoted spans, with exact extraction accuracy dropping below 40% in technical domains. In contrast, our approach achieves near-perfect extraction faithfulness regardless of the model used. Although enforcing hard constraints introduces a trade-off with fluency-oriented metrics, our method improves exact answer correctness and remains competitive overall, highlighting its suitability for safety-critical information retrieval applications.

Related papers

• WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval [11.681276883454288]
  We propose Wildcard Inference with Dynamic Expansion (WIDE) to overcome the problem of forced hallucination in cross-modal retrieval.<n>During the decoding generation phase, Asymmetry-aware Wildcard Decoding (AWD) detects semantic blind spots and emits wildcards instead of forced deterministic identifiers.<n>Blind-Spot Re-ranking (BSR) evaluates the expanded candidate pool using a hybrid scoring mechanism that combines discrete generation confidence with continuous semantic similarity.
  arXiv  Detail & Related papers  (2026-09-03T08:55:05Z)
• UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation [90.0896070825457]
  We propose a unified noise-driven framework that rethinks safety mechanisms through the lens of noise dynamics in diffusion processes.<n>Our key insight is that early-stage predicted noise exhibits inherent separability between normal and sexually explicit content.<n>We develop a lightweight noise-based detector achieving superior accuracy with virtually no computational overhead.
  arXiv  Detail & Related papers  (2026-07-18T14:03:39Z)
• REAL-OW: Rehearsal-free Open World Object Detection with Low-Rank Adaptation and Dual-Stage Objectness Modeling [56.888597798431704]
  Open-World Object Detection (OWOD) requires detectors to identify previously unseen objects as unknown and incrementally incorporate them into the set of known categories.<n>Existing frameworks rely heavily on exemplar replay to mitigate catastrophic forgetting, but in some real applications, storing raw data conflicts with data access restrictions and leads to data exposure risks.<n>We propose REAL-OW, a novel rehearsal-free framework that decouples incremental knowledge through a collaborative adapter architecture.
  arXiv  Detail & Related papers  (2026-07-03T06:38:54Z)
• Latent Abstraction for Retrieval-Augmented Generation [4.6096940605642915]
  Existing systems rely on generating natural language queries at each hop.<n>We propose textbfLAnR (Latent Abstraction for RAG), a unified framework in which a single LLM jointly performs encoding, retrieval, and generation entirely within its own latent space.
  arXiv  Detail & Related papers  (2026-04-20T06:26:13Z)
• DiffuGR: Generative Document Retrieval with Diffusion Language Models [80.78126312115087]
  We propose generative document retrieval with diffusion language models, dubbed DiffuGR.<n>For inference, DiffuGR attempts to generate DocID tokens in parallel and refine them through a controllable number of denoising steps.<n>In contrast to conventional left-to-right auto-regressive decoding, DiffuGR provides a novel mechanism to first generate more confident DocID tokens.
  arXiv  Detail & Related papers  (2025-11-11T12:00:09Z)
• Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation [108.13261761812517]
  We introduce FRANQ (Faithfulness-based Retrieval Augmented UNcertainty Quantification), a novel method for hallucination detection in RAG outputs.<n>We present a new long-form Question Answering (QA) dataset annotated for both factuality and faithfulness.
  arXiv  Detail & Related papers  (2025-05-27T11:56:59Z)
• Cognitive-Aligned Document Selection for Retrieval-augmented Generation [2.9060210098040855]
  We propose GGatrieval to dynamically update queries and filter high-quality, reliable retrieval documents.<n>We parse the user query into its syntactic components and perform fine-grained grounded alignment with the retrieved documents.<n>Our approach introduces a novel criterion for filtering retrieved documents, closely emulating human strategies for acquiring targeted information.
  arXiv  Detail & Related papers  (2025-02-17T13:00:15Z)
• RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation [21.764973680014368]
  RetroLLM is a unified framework that integrates retrieval and generation into a single, cohesive process.<n>To mitigate false pruning in the process of constrained evidence generation, we introduce hierarchical FM-Index constraints.<n>Experiments on five open-domain QA datasets demonstrate RetroLLM's superior performance across both in-domain and out-of-domain tasks.
  arXiv  Detail & Related papers  (2024-12-16T16:03:25Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• Generation-Augmented Retrieval for Open-domain Question Answering [134.27768711201202]
  Generation-Augmented Retrieval (GAR) for answering open-domain questions. We show that generating diverse contexts for a query is beneficial as fusing their results consistently yields better retrieval accuracy. GAR achieves state-of-the-art performance on Natural Questions and TriviaQA datasets under the extractive QA setup when equipped with an extractive reader.
  arXiv  Detail & Related papers  (2020-09-17T23:08:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.