UniCoR: Modality Collaboration for Robust Cross-Language Hybrid Code Retrieval

• URL: http://arxiv.org/abs/2512.10452v1
• Date: Thu, 11 Dec 2025 09:15:38 GMT
• Title: UniCoR: Modality Collaboration for Robust Cross-Language Hybrid Code Retrieval
• Authors: Yang Yang, Li Kuang, Jiakun Liu, Zhongxin Liu, Yingjie Xia, David Lo,
• Abstract summary: We propose UniCoR, a self-supervised framework that learns Unified Code Representations framework to learn unified and robust code representations.<n>We show that UniCoR outperforms all baseline models, achieving an average improvement of 8.64% in MRR and 11.54% in MAP over the best-performing baseline.<n>UniCoR exhibits stability in hybrid code retrieval and generalization capability in cross-language scenarios.
• Score: 21.36577755250534
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective code retrieval is indispensable and it has become an important paradigm to search code in hybrid mode using both natural language and code snippets. Nevertheless, it remains unclear whether existing approaches can effectively leverage such hybrid queries, particularly in cross-language contexts. We conduct a comprehensive empirical study of representative code models and reveal three challenges: (1) insufficient semantic understanding; (2) inefficient fusion in hybrid code retrieval; and (3) weak generalization in cross-language scenarios. To address these challenges, we propose UniCoR, a novel self-supervised framework that learns Unified Code Representations framework designed to learn unified and robust code representations. Firstly, we design a multi-perspective supervised contrastive learning module to enhance semantic understanding and modality fusion. It aligns representations from multiple perspectives, including code-to-code, natural language-to-code, and natural language-to-natural language, enforcing the model to capture a semantic essence among modalities. Secondly, we introduce a representation distribution consistency learning module to improve cross-language generalization, which explicitly aligns the feature distributions of different programming languages, enabling language-agnostic representation learning. Extensive experiments on both empirical benchmark and large-scale benchmark show that UniCoR outperforms all baseline models, achieving an average improvement of 8.64% in MRR and 11.54% in MAP over the best-performing baseline. Furthermore, UniCoR exhibits stability in hybrid code retrieval and generalization capability in cross-language scenarios.

Related papers

• Readability-Robust Code Summarization via Meta Curriculum Learning [53.44612630063336]
  In the real world, code is often poorly structured or obfuscated, significantly degrading model performance.<n>We propose RoFTCodeSum, a novel fine-tuning method that enhances the robustness of code summarization against poorly readable code.
  arXiv  Detail & Related papers  (2026-01-09T02:38:24Z)
• ChiEngMixBench: Evaluating Large Language Models on Spontaneous and Natural Chinese-English Code-Mixed Generation [0.0]
  We introduce ChiEngMixBench, the first benchmark designed to evaluate code-mixing ability in authentic community contexts.<n>ChiEngMixBench formulates code-mixing as a cognitive alignment problem, characterized by two complementary signals: Spontaneity and Naturalness.
  arXiv  Detail & Related papers  (2026-01-02T08:18:27Z)
• M2G-Eval: Enhancing and Evaluating Multi-granularity Multilingual Code Generation [42.21777678623796]
  We introduce M2G-Eval, a framework for evaluating code generation in large language models (LLMs) across four levels: Class, Function, Block, and Line.<n>M2G-Eval includes 17K+ training tasks and 1,286 human-annotated, contamination-controlled test instances.
  arXiv  Detail & Related papers  (2025-12-27T16:00:46Z)
• Completion by Comprehension: Guiding Code Generation with Multi-Granularity Understanding [37.78627994991325]
  CoCo is a novel framework that enables code Completion by of multi-granularity context from large-scale code repositories.<n>Experiments on CrossCodeEval and RepoEval benchmarks demonstrate that CoCo consistently surpasses state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-12-04T07:37:59Z)
• SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models [59.90381306452982]
  evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer.<n>We introduce SWE-1, a comprehensive benchmark that unifies heterogeneous code-related evaluations into a structured and production-aligned framework.<n>SWE- spans 8 task types, 8 programming scenarios, and 10 programming languages, with 2000 high-quality instances curated from authentic GitHub pull requests.
  arXiv  Detail & Related papers  (2025-11-07T18:01:32Z)
• Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning [81.43257201833154]
  We propose Bi-IRRA: a Bidirectional Implicit Relation Reasoning and Aligning framework to learn alignment across languages and modalities.<n>Within Bi-IRRA, a bidirectional implicit relation reasoning module enables bidirectional prediction of masked image and text.<n>The proposed method achieves new state-of-the-art results on all multilingual TIPR datasets.
  arXiv  Detail & Related papers  (2025-10-20T16:01:11Z)
• EMMA: Efficient Visual Alignment in Multi-Modal LLMs [56.03417732498859]
  EMMA is a lightweight cross-modality module designed to efficiently fuse visual and textual encodings.<n>EMMA boosts performance across multiple tasks by up to 9.3% while significantly improving robustness against hallucinations.
  arXiv  Detail & Related papers  (2024-10-02T23:00:31Z)
• Multi-Programming Language Ensemble for Code Generation in Large Language Model [5.882816711878273]
  Large language models (LLMs) have significantly improved code generation, particularly in one-pass code generation. Most existing approaches focus solely on generating code in a single programming language, overlooking the potential of leveraging the multi-language capabilities of LLMs. We propose Multi-Programming Language Ensemble (MPLE), a novel ensemble-based method that utilizes code generation across multiple programming languages to enhance overall performance.
  arXiv  Detail & Related papers  (2024-09-06T08:31:18Z)
• CART: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling [53.97609687516371]
  Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data.<n>Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the score between queries and candidates.<n>We propose a generative cross-modal retrieval framework (CART) based on coarse-to-fine semantic modeling.
  arXiv  Detail & Related papers  (2024-06-25T12:47:04Z)
• LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments [70.91258869156353]
  We introduce LangSuitE, a versatile and simulation-free testbed featuring 6 representative embodied tasks in textual embodied worlds. Compared with previous LLM-based testbeds, LangSuitE offers adaptability to diverse environments without multiple simulation engines. We devise a novel chain-of-thought (CoT) schema, EmMem, which summarizes embodied states w.r.t. history information.
  arXiv  Detail & Related papers  (2024-06-24T03:36:29Z)
• Contrastive Prompt Learning-based Code Search based on Interaction Matrix [5.379749366580253]
  We propose CPLCS, a contrastive prompt learning-based code search method based on the cross-modal interaction mechanism. We conduct extensive experiments to evaluate the effectiveness of our approach on a real-world dataset across six programming languages.
  arXiv  Detail & Related papers  (2023-10-10T06:24:52Z)
• Multilingual Conceptual Coverage in Text-to-Image Models [98.80343331645626]
  "Conceptual Coverage Across Languages" (CoCo-CroLa) is a technique for benchmarking the degree to which any generative text-to-image system provides multilingual parity to its training language in terms of tangible nouns. For each model we can assess "conceptual coverage" of a given target language relative to a source language by comparing the population of images generated for a series of tangible nouns in the source language to the population of images generated for each noun under translation in the target language.
  arXiv  Detail & Related papers  (2023-06-02T17:59:09Z)
• A Syntax-Guided Multi-Task Learning Approach for Turducken-Style Code Generation [19.489202790935902]
  We propose a syntax-guided multi-task learning approach TurduckenGen. Specifically, we first explicitly append the type information to the code tokens to capture the representation of syntactic constraints. Then we formalize code generation with syntactic constraint representation as an auxiliary task to enable the model to learn the syntactic constraints of the code.
  arXiv  Detail & Related papers  (2023-03-09T06:22:07Z)
• A Comprehensive Understanding of Code-mixed Language Semantics using Hierarchical Transformer [28.3684494647968]
  We propose a hierarchical transformer-based architecture (HIT) to learn the semantics of code-mixed languages. We evaluate the proposed method across 6 Indian languages and 9 NLP tasks on 17 datasets.
  arXiv  Detail & Related papers  (2022-04-27T07:50:18Z)

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.