论文研究
arxiv.org ·
精确反馈并非控制：评估大型语言模型中基于文本的闭环修订
该 arXiv 预印本提出固定预算的闭环修订协议，用确定性验证器报告精确长度、词汇和组合约束下的全部剩余违规，从而在反馈正确且完整的前提下隔离模型侧修订行为。在 19 个开源与闭源模型上，控制器级最终联合成功率从 17.4% 到 99.8% 不等，相同初始草稿下跨模型差距显著。受控实验显示模型对精确反馈有可复现的特定响应，后训练与规模会改变这些响应但未必更接近精确修正。失败轨迹常重复先前输出，且先前重复与后续可恢复性降低相关；匹配状态干预表明移除早期对话可改变重复逃逸，但不稳定提升最终成功率。作者结论是精确反馈使修订错误可观测，却不足以让闭环可靠。
AI推荐理由 arXiv 预印本，摘要给出明确实验设计：固定预算修订协议、确定性验证器、19 个开源与闭源模型，报告控制器级最终联合成功率 17.4%–99.8%，并指出失败轨迹常重复先前输出、先前重复与后续可恢复性降低相关。新信息在于把反馈正确性与完整性固定后隔离模型侧修订行为，并给出匹配状态干预结果；局限是仅摘要，未提供具体模型清单、任务细节与统计显著性，结论为预印本阶段。
78
正文
Computer Science > Computation and Language
arXiv:2609.28150 (cs)
[Submitted on 23 Sep 2026]
Title:Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs
Authors:Haitong Jiang, Chunlin Liu, Yile Wang, Yuhong Feng
View a PDF of the paper titled Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs, by Haitong Jiang and 3 other authors
View PDF
HTML (experimental)
Abstract:Closed-loop revision is increasingly used in large language model (LLM) applications, but failures may reflect incomplete feedback or ineffective responses to correct feedback. We introduce a fixed-budget revision protocol with deterministic verifiers that report all remaining violations across exact-length, lexical, and compositional constraints. Fixing feedback correctness and completeness isolates model-side revision behavior. Across 19 open- and closed-source models, controller-level mean final joint success ranges from 17.4% to 99.8%, with substantial cross-model gaps persisting under identical initial drafts. Controlled experiments reveal reproducible model-specific responses to exact feedback. Post-training and scale reshape these responses without consistently bringing them closer to exact correction. Across all constraint families, failed trajectories often repeat earlier outputs, and prior recurrence is associated with lower subsequent recoverability. Matched-state interventions show that removing earlier dialogue while holding the current draft and feedback fixed changes recurrence escape without reliably improving final success; effects depend on the model, task, and trigger-state composition. Exact feedback makes revision errors observable, but does not make the closed loop reliable. Code and reproduction instructions: this https URL.
Comments:
Subjects:
Computation and Language (cs.CL)
Cite as:
arXiv:2609.28150 [cs.CL]
(or
arXiv:2609.28150v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.28150
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Haitong Jiang [view email]
[v1]
Wed, 23 Sep 2026 14:06:52 UTC (815 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs, by Haitong Jiang and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)