ProtoLIP: From Sentence-Level to Object-Level Evidence Disentanglement

• URL: http://arxiv.org/abs/2609.16284v1
• Date: Mon, 14 Sep 2026 19:39:57 GMT
• Title: ProtoLIP: From Sentence-Level to Object-Level Evidence Disentanglement
• Abstract summary: We introduce textbfProtoLIP, a lightweight prototype-mediated evidence layer.<n>ProtoLIP organizes reusable visual prototypes into text-derived semantic families.<n>ProtoLIP constructs its matching score directly from localized prototype evidence.
• Score: 32.493558609275546
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Query-conditioned vision--language models enable fine-grained interpretation by revealing how visual evidence changes with textual queries. However, evidence conditioned on complete descriptions does not necessarily resolve into object-specific evidence, nor does an exposed evidence map necessarily identify the evidence that constitutes the model's prediction. Across multiple VLM architectures and independent benchmarks, we find that object-level queries often retain evidence from co-occurring objects and shared context. In this paper, we introduce \textbf{ProtoLIP}, a lightweight prototype-mediated evidence layer that organizes reusable visual prototypes into text-derived semantic families and uses query-dependent family routing to constrain which prototypes may provide evidence. Without spatial annotations or backbone retraining, ProtoLIP improves evidence localization and separation across query granularities, with localization gains transferring to independently pretrained VLMs with well-aligned patch--text representations. Despite using only text-derived weak supervision, ProtoLIP remains competitive with a spatially supervised grounding model while maintaining strong matching and competitive image--text retrieval. Crucially, ProtoLIP constructs its matching score directly from localized prototype evidence, enabling the score to be exactly decomposed into semantic-family and prototype contributions.

Related papers

• SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding [61.02068339726333]
  We propose SAGE, an evidence-grounded multi-agent framework for Chinese ancient document understanding.<n>SAGE coordinates specialized agents for task-aware planning, tool-mediated evidence acquisition, claim-level verification, and bounded replanning.<n> Experiments on the AncientDoc benchmark show that SAGE consistently outperforms matched direct-answering baselines.
  arXiv  Detail & Related papers  (2026-08-25T03:01:51Z)
• ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval [62.80735412748694]
  ConceptFormer is a latent concept representation learning framework for visual document retrieval.<n>It query-relevant evidence as continuous, query-conditioned latent concepts that explicitly bridge localized visual evidence and semantic relevance.<n>It achieves 16.7% and 22.1% relative improvements in average NDCG@10 over the strongest visual retrieval baseline and the strongest OCR-based text retrieval baseline, respectively.
  arXiv  Detail & Related papers  (2026-08-16T12:07:12Z)
• HiEviDR-Bench: A Benchmark for Hierarchical Evidence Aggregation in Deep Research [52.87128503345243]
  We introduce HiEviDR-Bench, a benchmark for evaluating Hierarchical Evidence Aggregation in Deep Research.<n>HiEviDR-Bench represents each instance with an explicit evidence graph that captures evidence selection, cross-source linking, and aggregation.<n>We develop a traceability-oriented evaluation framework with five dimensions: report quality, evidence traceability, citation accuracy, claim verification, and answer correctness.
  arXiv  Detail & Related papers  (2026-07-27T23:50:46Z)
• SPORT: Structure-Aware Prototype Disentanglement for Incomplete Multi-View Clustering [51.01038967474103]
  Prototype-based Incomplete Multi-view Clustering has attracted increasing attention by exploiting prototypes as semantic anchors for missing-view imputation.<n>We propose a novel framework termed Structure-aware PrOtotype disentanglement foR incomplete multi-view clusTering (SPORT)<n>SPORT explicitly disentangles shared and view-specific components of prototypes while preserving cluster-level relational structures.
  arXiv  Detail & Related papers  (2026-07-11T17:40:22Z)
• SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models [63.28435103335999]
  We introduce SOCO, a new benchmark for Semantic Object Correspondence.<n>We show that vision foundation backbones encode strong semantic structure but transfer correspondences poorly across related categories.<n>We also show that LVLMs are stronger at text-prompted part localization than at visual-reference cross-image matching.
  arXiv  Detail & Related papers  (2026-05-29T17:58:48Z)
• Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation [74.0621258662676]
  We propose Ptah, a multi-agent harness for interleaved report generation.<n>Ptah orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages.<n>A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow.
  arXiv  Detail & Related papers  (2026-05-28T12:40:34Z)
• Model-Document Protocol for AI Search [11.377241012645994]
  We introduce the Model-Document Protocol (MDP), a general framework that formalizes how raw text is bridged to large language models (LLMs)<n>Rather than treating retrieval as passage fetching, MDP defines multiple pathways that transform unstructured documents into task-specific, LLM-ready inputs.<n>As an instantiation, we present MDP-Agent, which realizes the protocol through an agentic process.
  arXiv  Detail & Related papers  (2025-10-29T04:29:17Z)
• ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering [30.65960340061612]
  Prototype-based modeling has shown promise for interpretability by grounding predictions in semantically meaningful regions.<n>We present ProtoVQA, a unified framework that learns question-aware prototypes that serve as reasoning anchors.<n>We propose the Visual-Linguistic Alignment Score (VLAS), which measures how well the model's attended regions align with ground-truth evidence.
  arXiv  Detail & Related papers  (2025-09-20T13:12:08Z)
• Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models [9.664217498808338]
  We introduce a unified taxonomy of evidence-based text generation with large language models.<n>We investigate 300 evaluation metrics across seven key dimensions.<n>We highlight open challenges and outline promising directions for future work.
  arXiv  Detail & Related papers  (2025-08-21T09:36:35Z)
• Unstructured Evidence Attribution for Long Context Query Focused Summarization [53.08341620504465]
  We propose to extract unstructured (i.e., spans of any length) evidence in order to acquire more relevant and consistent evidence than in the fixed granularity case.<n>We show how existing systems struggle to copy and properly cite unstructured evidence, which also tends to be "lost-in-the-middle"
  arXiv  Detail & Related papers  (2025-02-20T09:57:42Z)
• Graph-based Retrieval for Claim Verification over Cross-Document Evidence [0.6853165736531939]
  We conjecture that a graph-based approach can be beneficial to identify fragmented evidence. We tested this hypothesis by building, over the whole corpus, a large graph that interconnects text portions by means of mentioned entities. Our experiments show that leveraging on a graph structure is beneficial in identifying a reasonably small portion of passages related to a claim.
  arXiv  Detail & Related papers  (2021-09-13T14:54:26Z)

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.