Understanding Robustness of Model Editing in Code LLMs: An Empirical Study

• URL: http://arxiv.org/abs/2511.03182v1
• Date: Wed, 05 Nov 2025 04:58:13 GMT
• Title: Understanding Robustness of Model Editing in Code LLMs: An Empirical Study
• Authors: Vinaik Chhetri, A. B Siddique, Umar Farooq,
• Abstract summary: We present a systematic study of five state-of-the-art model editing methods.<n>We apply these methods to three leading open-source code LLMs, CodeLlama, CodeQwen1.5, and DeepSeek-Coder.<n>Instant edits consistently degrade model performance, with syntactic validity dropping by up to 86 percentage points and functional correctness declining by 45 points even in the best-performing setting.
• Score: 1.5624785508022727
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly used in software development. However, while LLMs remain static after pretraining, programming languages and APIs continue to evolve, leading to the generation of deprecated or incompatible code that undermines reliability. Retraining LLMs from scratch to reflect such changes is computationally expensive, making model editing a promising lightweight alternative that updates only a small subset of parameters. Despite its potential, it remains unclear whether model editing yields genuine syntactic and semantic adaptations or merely superficial fixes. In this work, we present a systematic study of five state-of-the-art model editing methods: Constrained Fine-Tuning (FT), GRACE, MEMIT, PMET, and ROME. We apply these methods to three leading open-source code LLMs, CodeLlama, CodeQwen1.5, and DeepSeek-Coder, under controlled API deprecation scenarios. Our evaluation covers both instant and sequential editing settings, using three disjoint evaluation sets designed to assess reliability, generalization, and specificity. We measure model correctness at three levels: successful compilation, partial test case pass, and full test pass. Our findings show that instant edits consistently degrade model performance, with syntactic validity dropping by up to 86 percentage points and functional correctness declining by 45 points even in the best-performing setting. Sequential edits further amplify this degradation, and in some cases, model performance collapses entirely. Across all models, most passing generations relied on workarounds rather than correctly adopting the intended changes, while faulty adoptions that result in test failures or compilation errors were significantly more frequent. Correct adoptions, where the model correctly integrates the intended change, occurred in only about 6% of cases.

Related papers

• PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise [60.63315470285562]
  MiniTruePrefixes is a novel specialized model that better detects factual inconsistencies over text prefixes.<n>We show that integrating MiniTruePrefixes into a controlled decoding framework substantially improves factual consistency in abstractive summarization.
  arXiv  Detail & Related papers  (2025-11-03T09:07:44Z)
• STABLE: Gated Continual Learning for Large Language Models [0.0]
  STABLE is a gated continual self editing framework that constrains forgetting during sequential updates.<n>Each candidate edit is evaluated against a stability budget using one of three metrics.<n>Experiments on the Qwen-2.5-7B model show that gating effectively mitigates forgetting while preserving adaptability.
  arXiv  Detail & Related papers  (2025-10-17T16:14:05Z)
• Probing Pre-trained Language Models on Code Changes: Insights from ReDef, a High-Confidence Just-in-Time Defect Prediction Dataset [0.0]
  We present ReDef, a high-confidence benchmark of function-level modifications curated from 22 large-scale C/C++ projects.<n>Defective cases are anchored by revert commits, while clean cases are validated through post-hoc history checks.<n>This pipeline yields 3,164 defective and 10,268 clean modifications, offering substantially more reliable labels than prior existing resources.
  arXiv  Detail & Related papers  (2025-09-11T07:07:11Z)
• The Mirage of Model Editing: Revisiting Evaluation in the Wild [70.17413507444704]
  We introduce QAEdit, a new benchmark aligned with widely used question answering (QA) datasets, and WILD, a task-agnostic evaluation framework.<n>Our single editing experiments show that current editing methods perform substantially worse than previously reported.
  arXiv  Detail & Related papers  (2025-02-16T15:57:55Z)
• Rethinking the Residual Distribution of Locate-then-Editing Methods in Model Editing [14.958557185068]
  Model editing enables targeted updates to the knowledge of large language models.<n> locate-then-edit methods first identify critical layers, then compute residuals at the final critical layer based on the target edit.<n> residual distribution, a core mechanism in these methods, introduces weight shift errors that undermine editing precision.<n>We propose the BLUE strategy to enhance locate-then-edit methods.
  arXiv  Detail & Related papers  (2025-02-06T03:20:17Z)
• Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering [19.019004855931676]
  Large language models (LLMs) have confirmed their effectiveness in the code generation task with promising results. Their performance on adaptation, a reuse-oriented and context-dependent code change prediction task, is still unclear. We propose an interactive prompting approach to elicit LLMs' adaptation ability.
  arXiv  Detail & Related papers  (2024-11-23T09:40:36Z)
• Exploring Data-Efficient Adaptation of Large Language Models for Code Generation [64.5583894165813]
  We propose a novel adaptation approach named DEED, which stands for Data-Efficient adaptation with Error-Driven learning for code generation.<n> Experimental results show that, compared to other mainstream fine-tuning approaches, DEED achieves superior performance with few training data.
  arXiv  Detail & Related papers  (2024-02-29T16:09:02Z)
• The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse [58.0132400208411]
  Even a single edit can trigger model collapse, manifesting as significant performance degradation in various benchmark tasks. benchmarking Large Language Models after each edit is impractically time-consuming and resource-intensive. We have utilized GPT-3.5 to develop a new dataset, HardEdit, based on hard cases.
  arXiv  Detail & Related papers  (2024-02-15T01:50:38Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)
• Memory-Based Model Editing at Scale [102.28475739907498]
  Existing model editors struggle to accurately model an edit's intended scope. We propose Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model (SERAC) SERAC stores edits in an explicit memory and learns to reason over them to modulate the base model's predictions as needed.
  arXiv  Detail & Related papers  (2022-06-13T23:40:34Z)

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.