Diyin Tang

Zijun Jia, Yuanchang Ye, Sen Jia et al.

Large language models (LLMs) can enhance factuality via retrieval-augmented generation (RAG), but applying RAG to every query is unnecessary when the model-only answer is reliable. This motivates cascaded RAG: each query is first handled by an LLM-only branch, escalated to a RAG fallback only if the primary branch is uncertain, and abstained from when neither branch is sufficiently trustworthy. However, calibrating such cascades stage by stage may be conservative, since the final utility depends on joint uncertainty thresholding of LLM-only and RAG. In this work, we develop BalanceRAG to certify threshold pairs at a target risk level. Given uncertainty scores from the two branches, BalanceRAG frames each threshold pair as an operating point on a two-dimensional lattice and identifies safe operating points using sequential graphical testing. This enables risk-adaptive threshold calibration, controlling the system-level error rate among accepted points, while retaining more examples. Furthermore, BalanceRAG extends to multi-risk calibration, allowing retrieval usage to be bounded together with the selection-conditioned risk. Experiments on three open-domain question answering (QA) benchmarks across multiple LLM backbones demonstrate that BalanceRAG meets prescribed risk levels, preserves higher coverage and more accepted correct examples, and reduces unnecessary retrieval calls compared with always-on RAG.

Zijun Jia, Jinsong Yu, Hongyu Long et al.

Road rage, often triggered by emotional suppression and sudden outbursts, significantly threatens road safety by causing collisions and aggressive behavior. Speech emotion recognition technologies can mitigate this risk by identifying negative emotions early and issuing timely alerts. However, current SER methods, such as those based on hidden markov models and Long short-term memory networks, primarily handle one-dimensional signals, frequently experience overfitting, and lack calibration, limiting their safety-critical effectiveness. We propose a novel risk-controlled prediction framework providing statistically rigorous guarantees on prediction accuracy. This approach employs a calibration set to define a binary loss function indicating whether the true label is included in the prediction set. Using a data-driven threshold $β$, we optimize a joint loss function to maintain an expected test loss bounded by a user-specified risk level $α$. Evaluations across six baseline models and two benchmark datasets demonstrate our framework consistently achieves a minimum coverage of $1 - α$, effectively controlling marginal error rates despite varying calibration-test split ratios (e.g., 0.1). The robustness and generalizability of the framework are further validated through an extension to small-batch online calibration under a local exchangeability assumption. We construct a non-negative test martingale to maintain prediction validity even in dynamic and non-exchangeable environments. Cross-dataset tests confirm our method's ability to uphold reliable statistical guarantees in realistic, evolving data scenarios.