A new auditing framework measures how much of the public's submitted viewpoints is lost in AI-generated consultation summaries, finding that official summaries represent the population worse than a random set of participants and that critical voices are most likely excluded.
ACM computing surveys , volume=
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 12roles
background 1polarities
background 1representative citing papers
Audit of ChatGPT, Copilot, Gemini and Perplexity finds ~16% of cited sources are AI-generated across 712 queries on politics, health and environment.
BalanceRAG uses sequential graphical testing on a 2D lattice of threshold pairs to certify safe operating points that meet target risk levels in cascaded RAG while increasing coverage.
Proposes a three-level taxonomy of Cultural Awareness, Cultural Sensitivity, and Cultural Competence for AI evaluation, grounded in intercultural communication scholarship to improve validity in multicultural contexts.
A test-driven pipeline with an auto-constructed privacy feature library detects 2.56 times more confirmed privacy leaks in LLM-based code generation than existing baselines.
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
LUCID detects hallucinations in LLM-KG reasoning by extracting node/edge features from attention and semantics then integrating them with KG structure in a GNN, achieving SOTA on nine new benchmark datasets versus 15 baselines.
R³AG routes queries to retrievers by decomposing capabilities into retrieval quality and generation utility, trained via contrastive learning on document assessments and downstream answer correctness to outperform static methods.
PairCoder is a two-agent pair-programming method that leverages toolchain verification oracles to improve LLM generation of verifiable structured artifacts on 17 benchmarks across seven models.
C3RL is a new RL algorithm combining correctness, calibration, and reference accuracy rewards to improve LLM confidence calibration, enabling CAS to outperform majority voting with up to 12.33x lower inference cost.
AROMA combines text, graph topology, and protein sequences with augmented reasoning and two-stage optimization to deliver more accurate and interpretable predictions of genetic perturbation effects in virtual cells, outperforming baselines even in zero-shot and long-tail settings.
citing papers explorer
-
Participatory provenance as representational auditing for AI-mediated public consultation
A new auditing framework measures how much of the public's submitted viewpoints is lost in AI-generated consultation summaries, finding that official summaries represent the population worse than a random set of participants and that critical voices are most likely excluded.
-
Synthetic Sources?: Auditing Generative Search Engine Citations for Evidence of AI-Generated Sources
Audit of ChatGPT, Copilot, Gemini and Perplexity finds ~16% of cited sources are AI-generated across 712 queries on politics, health and environment.
-
BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation
BalanceRAG uses sequential graphical testing on a 2D lattice of threshold pairs to certify safe operating points that meet target risk levels in cascaded RAG while increasing coverage.
-
Defining Cultural Capabilities for AI Evaluation: A Taxonomy Grounded in Intercultural Communication Theory
Proposes a three-level taxonomy of Cultural Awareness, Cultural Sensitivity, and Cultural Competence for AI evaluation, grounded in intercultural communication scholarship to improve validity in multicultural contexts.
-
Probing Privacy Leaks in LLM-based Code Generation via Test Generation
A test-driven pipeline with an auto-constructed privacy feature library detects 2.56 times more confirmed privacy leaks in LLM-based code generation than existing baselines.
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
-
Detecting Hallucinations for Large Language Model-based Knowledge Graph Reasoning
LUCID detects hallucinations in LLM-KG reasoning by extracting node/edge features from attention and semantics then integrating them with KG structure in a GNN, achieving SOTA on nine new benchmark datasets versus 15 baselines.
-
R$^3$AG: Retriever Routing for Retrieval-Augmented Generation
R³AG routes queries to retrievers by decomposing capabilities into retrieval quality and generation utility, trained via contrastive learning on document assessments and downstream answer correctness to outperform static methods.
-
PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation
PairCoder is a two-agent pair-programming method that leverages toolchain verification oracles to improve LLM generation of verifiable structured artifacts on 17 benchmarks across seven models.
-
Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scaling
C3RL is a new RL algorithm combining correctness, calibration, and reference accuracy rewards to improve LLM confidence calibration, enabling CAS to outperform majority voting with up to 12.33x lower inference cost.
-
AROMA: Augmented Reasoning Over a Multimodal Architecture for Virtual Cell Genetic Perturbation Modeling
AROMA combines text, graph topology, and protein sequences with augmented reasoning and two-stage optimization to deliver more accurate and interpretable predictions of genetic perturbation effects in virtual cells, outperforming baselines even in zero-shot and long-tail settings.