BIRDS framework quantifies request-level biodiversity impacts of LLM serving via operational and embodied pathways and introduces QNBI to jointly assess impact and quality, showing accumulation at scale across workloads, models, GPUs, and regions.
Crosscodeeval: A diverse and multilingual benchmark for cross-file code completion
7 Pith papers cite this work, alongside 10 external citations. Polarity classification is still indexing.
7
Pith papers citing it
10
external citations · external index
citation-role summary
background 2
dataset 1
citation-polarity summary
years
2026 7representative citing papers
Stale repository context in code RAG actively induces models to produce obsolete helper references, raising stale outputs by 76-88 percentage points over current-only retrieval in a 17-sample diagnostic study.
R2ABench benchmark shows LLMs generate syntactically valid software architectures from requirements but produce structurally fragmented results due to weak relational reasoning.
Code2LoRA generates repo-specific LoRA adapters via hypernetwork for code LMs, matching per-repo LoRA on static tasks and exceeding shared LoRA by 5.2 pp on evolving code in a 604-repo benchmark.
ATM is a CID-brokered governance framework that maps write intents to semantic atoms for pre-admission control, validation, and neutral-steward application in single-domain multi-agent code synthesis.
Function-based chunking underperforms other strategies in RAG code completion by 3.57-5.64 points, with context length as the dominant factor.
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.
citing papers explorer
-
BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving
BIRDS framework quantifies request-level biodiversity impacts of LLM serving via operational and embodied pathways and introduces QNBI to jointly assess impact and quality, showing accumulation at scale across workloads, models, GPUs, and regions.
-
When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context
Stale repository context in code RAG actively induces models to produce obsolete helper references, raising stale outputs by 76-88 percentage points over current-only retrieval in a 17-sample diagnostic study.
-
Benchmarking Requirement-to-Architecture Generation with Hybrid Evaluation
R2ABench benchmark shows LLMs generate syntactically valid software architectures from requirements but produce structurally fragmented results due to weak relational reasoning.
-
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
Code2LoRA generates repo-specific LoRA adapters via hypernetwork for code LMs, matching per-repo LoRA on static tasks and exceeding shared LoRA by 5.2 pp on evolving code in a 604-repo benchmark.
-
ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis
ATM is a CID-brokered governance framework that maps write intents to semantic atoms for pre-admission control, validation, and neutral-steward application in single-domain multi-agent code synthesis.
-
How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study
Function-based chunking underperforms other strategies in RAG code completion by 3.57-5.64 points, with context length as the dominant factor.
-
LLM-Oriented Information Retrieval: A Denoising-First Perspective
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.