Beyond Similarity: Task-Aligned Retrieval for Language Models

• URL: http://arxiv.org/abs/2605.27951v1
• Date: Wed, 27 May 2026 04:45:57 GMT
• Title: Beyond Similarity: Task-Aligned Retrieval for Language Models
• Abstract summary: Retrieval-augmented generation (RAG) ranks passages by semantic similarity to the input, implicitly assuming that semantic similarity is a reliable indication of applicability in downstream tasks.<n>We propose Task-Aligned Retrieval (TAG), a retrieval framework that replaces similarity-based retrieval with applicability-based rule selection.
• Score: 3.141210160384506
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-augmented generation (RAG) ranks passages by semantic similarity to the input, implicitly assuming that semantic similarity is a reliable indication of applicability in downstream tasks. This assumption breaks down when task success depends not on topical relevance but on applying the correct rules, constraints, or procedural guidance. In such settings, the most useful context may be the rule triggered by the input rather than the most semantically similar passage. We propose Task-Aligned Retrieval (TAG), a retrieval framework that replaces similarity-based retrieval with applicability-based rule selection. TAG transforms source documents into traceable condition-action rules, identifies which rules apply to a given input through pairwise LLM judgments, and generates the output conditioned only on the selected actions. We empirically observe that across Wikipedia NPOV rewriting, HumanEval with PEP~8 compliance, and NBA transaction reasoning on RuleArena, TAG consistently outperforms standard RAG, with the largest gains in high-mismatch settings (up to 12.2\%) while reducing retrieved context by up to 93\%. These results suggest that, in rule- and instruction-governed tasks, retrieval should optimize for applicability rather than for semantic similarity alone.

Related papers

• Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach [58.15427952222424]
  General-purpose text embeddings are widely deployed for such tasks, but broad semantic similarity can place semantically similar yet task-distinct examples.<n>We introduce Prototype-Guided Contrastive Learning (PGCL), a prototype-guided geometric regularization module built on top of frozen text embeddings.
  arXiv  Detail & Related papers  (2026-08-15T13:19:25Z)
• Constraint-Aware Hierarchical Search for Regulation-Driven Fine-Grained Classification [7.061842884221568]
  Tasks such as customs tariff classification, export control categorization, and standards-based equipment coding require assigning an input instance to a fine-grained class under an explicit regulatory hierarchy.<n>We formulate this setting as regulation-driven fine-grained hierarchical classification, where an external instance must be assigned to a fine-grained class through a valid path in a regulatory hierarchy and supported by auditable evidence.<n>We propose a constraint-aware hierarchical search framework that converts regulatory documents into a searchable tree, retrieves only valid local candidate nodes, and uses structured regulatory fields with evidence snippets to guide each next-hop decision.
  arXiv  Detail & Related papers  (2026-07-12T05:57:22Z)
• Beyond BLEU: A Semantic Evaluation Method for Code Translation [2.3802148866231057]
  We propose a novel evaluation methodology for code translation tasks, emphasizing semantic equivalence over surface-level string similarity.<n>We introduce a semantic correctness score, defined as the proportion of translations that produce correct execution outcomes.<n>Our findings show that LLM-based approaches significantly outperform ones, while BLEU scores show negligible correlation with semantic correctness.
  arXiv  Detail & Related papers  (2026-05-06T17:14:33Z)
• Semantic Entanglement in Vector-Based Retrieval: A Formal Framework and Context-Conditioned Disentanglement Pipeline for Agentic RAG Systems [0.0]
  We formalize semantic entanglement as a model-relative measure of cross-topic overlap in embedding space.<n>We introduce the Semantic Disentanglement Pipeline (SDP), a four-stage preprocessing framework that restructures documents prior to embedding.<n>We evaluate SDP on a real-world enterprise healthcare knowledge base comprising over 2,000 documents across approximately 25 sub-domains.
  arXiv  Detail & Related papers  (2026-04-20T00:24:34Z)
• Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs [55.78708003681562]
  Retrieval-Augmented Generation (RAG) mitigates hallucination in large language models (LLMs) by incorporating external knowledge during generation.<n>Existing RAG approaches typically retrieve and unstructured text fragments as context.<n>We propose Tri-RAG, a structured triplet-based retrieval framework that improves retrieval efficiency through reasoning-aligned context construction.
  arXiv  Detail & Related papers  (2026-04-14T11:36:29Z)
• Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity [42.873412319680035]
  This paper introduces a novel method for generating benchmarks to evaluate semantic similarity methods for Large Language Models outputs.<n>We generate benchmark datasets in four different domains (general knowledge, biomedicine, finance, biology)<n>We observe that the sub-type of semantic variation, as well as the domain of the benchmark impact the performance of semantic similarity methods.
  arXiv  Detail & Related papers  (2025-11-25T05:07:08Z)
• Knowledge Graph Completion with Relation-Aware Anchor Enhancement [50.50944396454757]
  We propose a relation-aware anchor enhanced knowledge graph completion method (RAA-KGC)<n>We first generate anchor entities within the relation-aware neighborhood of the head entity.<n>Then, by pulling the query embedding towards the neighborhoods of the anchors, it is tuned to be more discriminative for target entity matching.
  arXiv  Detail & Related papers  (2025-04-08T15:22:08Z)
• SparseCL: Sparse Contrastive Learning for Contradiction Retrieval [87.02936971689817]
  Contradiction retrieval refers to identifying and extracting documents that explicitly disagree with or refute the content of a query. Existing methods such as similarity search and crossencoder models exhibit significant limitations. We introduce SparseCL that leverages specially trained sentence embeddings designed to preserve subtle, contradictory nuances between sentences.
  arXiv  Detail & Related papers  (2024-06-15T21:57:03Z)
• RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical Rules [30.239044569301534]
  Weakly supervised text classification (WSTC) has attracted increasing attention due to its applicability in classifying a mass of texts. We propose a prompting PLM-based approach named RulePrompt for the WSTC task, consisting of a rule mining module and a rule-enhanced pseudo label generation module. Our approach yields interpretable category rules, proving its advantage in disambiguating easily-confused categories.
  arXiv  Detail & Related papers  (2024-03-05T12:50:36Z)
• Hierarchical Context Tagging for Utterance Rewriting [51.251400047377324]
  Methods that tag rather than linearly generate sequences have proven stronger in both in- and out-of-domain rewriting settings. We propose a hierarchical context tagger that mitigates this issue by predicting slotted rules. Experiments on several benchmarks show that HCT can outperform state-of-the-art rewriting systems by 2 BLEU points.
  arXiv  Detail & Related papers  (2022-06-22T17:09:34Z)
• Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning [61.32992639292889]
  Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. We introduce a new scoring method that casts a plausibility ranking task in a full-text format. We show that our method provides a much more stable training phase across random restarts.
  arXiv  Detail & Related papers  (2020-04-29T10:54:40Z)

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.