MSLA is the first physically deployable attack that uses adversarial lighting to break semantic alignment in VLMs such as CLIP, LLaVA, and BLIP, causing classification failures and hallucinations in real scenes.
Title resolution pending
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 19roles
background 1polarities
background 1representative citing papers
DDIPE poisons LLM agent skills by embedding malicious logic in documentation examples, achieving 11.6-33.5% bypass rates across frameworks while explicit attacks are blocked, with 2.5% evading detection.
Heimdallr detects seven LLM-induced threat vectors in GitHub CI via L-WPG graphs, triggerability analysis, and hybrid dataflow, with F1 0.917 on 300 labeled workflows and 802 disclosed cases.
uxCUA is a trained computer use agent that assesses GUI usability more accurately than larger models by learning to prioritize and execute important user interactions on labeled interface datasets.
PlayCoder raises the rate of LLM-generated GUI apps that can be played end-to-end without logic errors from near zero to 20.3% Play@3 by adding repository-aware generation, agent-driven testing, and iterative repair.
A dataset revealing high inter-designer disagreement on UI preferences motivates a sample-efficient method that personalizes generative interfaces by embedding new users in the space of prior designers, outperforming baselines in both modeling and user preference.
SAGE is a new multi-agent benchmark that formalizes service SOPs as dynamic dialogue graphs to measure LLM agents on logical compliance and path coverage, uncovering an execution gap and empathy resilience across 27 models in 6 scenarios.
GUIDE decomposes GUI agent evaluation into trajectory segmentation, subtask diagnosis, and overall summary to deliver higher accuracy and structured error reports than holistic baselines.
ClarifyCodeBench is a new benchmark with manual annotations and two metrics showing that LLMs strong at code generation are weak at clarifying ambiguous requirements, with performance worsening as ambiguity density rises.
An empirical study of 57 ML evaluation harnesses shows 41.4% of operational issues occur in the specification stage, driven mainly by unimplemented features, documentation gaps, and missing input validation.
Creates MediLongChat synthetic longitudinal medical dialogues and benchmarks showing state-of-the-art LLMs struggle with in-dialogue, cross-dialogue, and synthesis reasoning tasks.
AOCI creates an incremental symbolic-semantic index per code unit that gives LLMs a complete, consistent repository view, outperforming baselines with zero defects on 19 industrial tasks while using far fewer tokens.
MultEval supports collaborative creation of LLM-as-a-judge criteria by surfacing disagreements via consensus-building methods, allowing iterative revisions with examples and history, and keeping transparent how human judgments become automated rules.
PlayCoder combines a repository-aware coding agent with a vision-based GUI testing agent and an automated program repair loop to detect and fix silent logic errors in LLM-generated interactive application code.
Targeted, evidence-rich context partitions improve causal clarity and actionability of LLM failure explanations while large undifferentiated contexts produce vaguer outputs, with higher-quality explanations correlating to better downstream repair rates.
EvoRAG adds a feedback-driven backpropagation step that attributes response quality to individual knowledge-graph triplets and updates the graph to raise reasoning accuracy by 7.34 percent over prior KG-RAG methods.
LLM-based SE tools lack stable ground truth and deterministic outputs, making standard evaluation assumptions invalid and requiring new approaches for reliable assessment.
Binary groundedness judgments in AI evaluations should be replaced by a reader-centered taxonomy of support relations that distinguishes syntactic and interpretive moves between generated statements and source documents.
citing papers explorer
-
Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks
MSLA is the first physically deployable attack that uses adversarial lighting to break semantic alignment in VLMs such as CLIP, LLaVA, and BLIP, causing classification failures and hallucinations in real scenes.
-
Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
DDIPE poisons LLM agent skills by embedding malicious logic in documentation examples, achieving 11.6-33.5% bypass rates across frameworks while explicit attacks are blocked, with 2.5% evading detection.
-
Heimdallr: Characterizing and Detecting LLM-Induced Security Risks in GitHub CI Workflows
Heimdallr detects seven LLM-induced threat vectors in GitHub CI via L-WPG graphs, triggerability analysis, and hybrid dataflow, with F1 0.917 on 300 labeled workflows and 802 disclosed cases.
-
Training Computer Use Agents to Assess the Usability of Graphical User Interfaces
uxCUA is a trained computer use agent that assesses GUI usability more accurately than larger models by learning to prioritize and execute important user interactions on labeled interface datasets.
-
PlayCoder: Making LLM-Generated GUI Code Playable
PlayCoder raises the rate of LLM-generated GUI apps that can be played end-to-end without logic errors from near zero to 20.3% Play@3 by adding repository-aware generation, agent-driven testing, and iterative repair.
-
Efficient Personalization of Generative User Interfaces
A dataset revealing high inter-designer disagreement on UI preferences motivates a sample-efficient method that personalizes generative interfaces by embedding new users in the space of prior designers, outperforming baselines in both modeling and user preference.
-
SAGE: A Service Agent Graph-guided Evaluation Benchmark
SAGE is a new multi-agent benchmark that formalizes service SOPs as dynamic dialogue graphs to measure LLM agents on logical compliance and path coverage, uncovering an execution gap and empathy resilience across 27 models in 6 scenarios.
-
GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis
GUIDE decomposes GUI agent evaluation into trajectory segmentation, subtask diagnosis, and overall summary to deliver higher accuracy and structured error reports than holistic baselines.
-
ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation
ClarifyCodeBench is a new benchmark with manual annotations and two metrics showing that LLMs strong at code generation are weak at clarifying ambiguous requirements, with performance worsening as ambiguity density rises.
-
Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild
An empirical study of 57 ML evaluation harnesses shows 41.4% of operational issues occur in the specification stage, driven mainly by unimplemented features, documentation gaps, and missing input validation.
-
Synthesis and Evaluation of Long-term History-aware Medical Dialogue
Creates MediLongChat synthetic longitudinal medical dialogues and benchmarks showing state-of-the-art LLMs struggle with in-dialogue, cross-dialogue, and synthesis reasoning tasks.
-
AOCI: Symbolic-Semantic Indexing for Practical Repository-Scale Code Understanding with LLMs
AOCI creates an incremental symbolic-semantic index per code unit that gives LLMs a complete, consistent repository view, outperforming baselines with zero defects on 19 industrial tasks while using far fewer tokens.
-
MultEval: Supporting Collaborative Alignment for LLM-as-a-Judge Evaluation Criteria
MultEval supports collaborative creation of LLM-as-a-judge criteria by surfacing disagreements via consensus-building methods, allowing iterative revisions with examples and history, and keeping transparent how human judgments become automated rules.
-
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
PlayCoder combines a repository-aware coding agent with a vision-based GUI testing agent and an automated program repair loop to detect and fix silent logic errors in LLM-generated interactive application code.
-
From Program Slices to Causal Clarity: Evaluating Faithful, Actionable LLM-Generated Failure Explanations via Context Partitioning and LLM-as-a-Judge
Targeted, evidence-rich context partitions improve causal clarity and actionability of LLM failure explanations while large undifferentiated contexts produce vaguer outputs, with higher-quality explanations correlating to better downstream repair rates.
-
EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation
EvoRAG adds a feedback-driven backpropagation step that attributes response quality to individual knowledge-graph triplets and updates the graph to raise reasoning accuracy by 7.34 percent over prior KG-RAG methods.
-
Evaluation of LLM-Based Software Engineering Tools: Practices, Challenges, and Future Directions
LLM-based SE tools lack stable ground truth and deterministic outputs, making standard evaluation assumptions invalid and requiring new approaches for reliable assessment.
-
From Binary Groundedness to Support Relations: Towards a Reader-Centred Taxonomy for Comprehension of AI Output
Binary groundedness judgments in AI evaluations should be replaced by a reader-centered taxonomy of support relations that distinguishes syntactic and interpretive moves between generated statements and source documents.
- Safeguarding LLM Agents from Misalignment through Provenance Analysis