Internal-state probes enable truthfulness prediction before a large language model generates an answer. When detectors change both the layers they read and the rules used to combine them, the source of improved prediction becomes difficult to identify. We separate these choices and find that retaining more layers impro...
Zhi-Hao Guo, Zong-Han Wu, Huan Huo et al.· 0 citations
CorVer (Corpus Verify) is a lightweight training-time approach to process supervision that derives sentence-level rewards from corpus co-occurrence statistics and outperforms the unmodified models in all standard factual-QA settings.
Shi-Chen Fan, Hao-Chang Hao, De-Hai Min et al.· 5 citations
REMAP is proposed, a reflection-guided memory editing approach for online alignment of persona facts that selectively writes and revises memory entries based on the current dialogue evidence and retrieved related items, enabling more efficient context utilization over extended interaction horizons.
Qingyang Xu, Xiao Liu, Zhou Fang et al.· Annual International ACM SIG...· 0 citations
Evidence of cross-lingual efficacy of code-based LLMs for Chinese QA tasks, further enhanced through Code Llama-M's expanded Chinese vocabulary is found, and successful application of the fine-tuned LLM in a live assistant system, enhancing user experience is demonstrated.
Jiajun Yu, Linghan Zheng, Hui Liu et al.· Annual International ACM SIG...· 0 citations
HalluTracer is introduced, a detection framework that reads and aggregates truthfulness evidence across every layer of the forward pass before the model emits any answer token, recasts hallucination detection from a layer-selection problem into a depth-aggregation problem governed by the geometric sparsity of the truth...
Zhi-Hao Guo, Zong-Han Wu, Huan Huo et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
