arXiv:2605. 22864v2 Announce Type: replace Abstract: The maximum softmax probability (MSP) represents a default approach when evaluating uncertainty quantification for language model generation with structured output.
arXiv:2507. 06722v2 Announce Type: replace-cross Abstract: Understanding how large language models (LLMs) internally represent and process their predictions is central to detecting uncertainty and preventing hallucinations.
ActMap is a new white‑box representation that compresses the entire hidden‑state trajectory of a language model during generation into a fixed 12 × 32 × 128 tensor. This compact 96 KiB map can be captured with no overhead and is read by a lightweight Vision Transformer to estimate answer correctness in a fraction of a millisecond. In experiments on short‑answer QA, math, and summarization, ActMap outperforms sampling, token‑probability, attention, and embedding baselines and matches a larger ACT‑ViT detector while achieving lower calibration error on most test pairs.
arXiv:2608. 15448v1 Announce Type: cross Abstract: Large language models increasingly rely on sampling as a driver of their own improvement, making the fidelity of their learned distributions more critical than ever.
The paper introduces Prediction of Prediction (PoP), a method that fuses intermediate hidden representations across transformer layers during a single forward pass to detect hallucinations in large language models. PoP leverages internal hidden‑state transition dynamics to signal factual errors without extra decoding steps, achieving a 75.5% AUROC on the TruthfulQA benchmark with less than 1.2% added latency.
arXiv:2607. 00510v1 Announce Type: new Abstract: Knowing which training examples drive outputs is fundamental to auditing, correcting, and understanding language models, yet for modern LLMs this remains expensive, approximate, and largely post-hoc.
arXiv:2606. 27679v1 Announce Type: cross Abstract: Probe-based uncertainty estimation (UE) has emerged as a prominent approach to detect hallucinations in Large Language Models (LLMs) by learning uncertainty from internal model signals.
arXiv:2501.10573v2 Announce Type: replace-cross Abstract: We study the geometry of token representations at the prompt level in large language models through the lens of intrinsic dimension. Viewing...
arXiv:2604.11662v2 Announce Type: replace Abstract: Recent work has shown that the hidden states of large language models contain signals useful for uncertainty estimation, motivating a growing inter...
arXiv:2506. 07406v3 Announce Type: replace-cross Abstract: Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research.
arXiv:2603.18908v5 Announce Type: replace Abstract: Independently trained language models often learn compatible late-stage representations, despite differences in training objectives, architectures,...
arXiv:2606. 18383v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable features from language models (LMs), yet a central question remains: when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM We study this through a post-hoc generalization framework that certifies the LM via a sparse proxy, obtained by replacing a native hidden activation with its pretrained SAE reconstruction.
The paper investigates multilingual confidence calibration in large language models, revealing that non‑English languages are systematically less well calibrated than English. By analyzing internal representations, the authors find that late‑intermediate layers provide a more reliable confidence signal than the final layer, which is biased by English‑centric training. They propose training‑free methods such as Language‑Aware Confidence Ensemble (LACE) to adaptively select optimal layers per language, aiming to improve global equity and trustworthiness of LLMs.