Other people with similar names: Qi Cao, Qi Cao

Unverified author pages with similar names: Qi Cao


2026

As large language models (LLMs) are increasingly deployed, harmful generations have become a critical safety concern. Existing safeguards operate at the input, output, or streaming-generation stages, while early-risk methods that rely on surface tokens or output logits often suffer from weak initial signals, and internals-based detectors using dense representations may retain highly entangled and redundant safety-irrelevant information. It therefore remains unclear whether the earliest post-generation hidden states already contain reliable signals about final-response harmfulness. To address this gap, we propose ForeSight, a first-token output-risk forecasting framework that distills weak and redundant early safety signals into compact, layer-aware risk representations. Experiments across five safety benchmarks and two target models demonstrate that ForeSight achieves superior and efficient early-risk forecasting while using only first-token hidden states. The code is available at: https://anonymous.4open.science/r/Foresight-B067
Recent Large Audio Language Models (LALMs) demonstrate impressive performance on speech benchmarks, yet it remains unclear whether these models genuinely process acoustic signals or rely on text-based semantic inference. To systematically study this question, we introduce DEAF (Diagnostic Evaluation of Acoustic Faithfulness), a bench- mark of over 2,700 conflict stimuli spanning three acoustic dimensions: emotional prosody, background sounds, and speaker identity. Then, we design a controlled multi-level evaluation framework that progressively increases textual influence, ranging from semantic conflicts in the content to misleading prompts and their combination, allowing us to disentangle content-driven bias from prompt-induced sycophancy. We further introduce diagnostic metrics to quantify model reliance on textual cues over acoustic signals. Our evaluation of seven LALMs reveals a consistent pattern of text dominance: models are sensitive to acoustic variations, yet predictions are predominantly driven by textual inputs, revealing a gap between high performance on standard speech benchmarks and genuine acoustic understanding. Code and benchmark resources are publicly available at: https://github.com/kikixiong/DEAF