The paper investigates whether large language models can learn and reproduce annotator‑specific label‑explanation behavior, using two sentence‑pair tasks with four annotators each. It finds that individual annotator patterns are weak at the single‑annotation level but become detectable after reducing input‑content effects and aggregating across annotators. The authors propose cross‑annotator preference optimization (CAPO), which improves upon prompting and supervised fine‑tuning by better capturing annotator‑specific reasoning while maintaining stable attribution.
By Beiduo Chen, Pingjun Hong, Ziyun Zhang, Benjamin Roth, Anna Korhonen, Barbara Plank
arXiv:2602. 11852v2 Announce Type: replace Abstract: While state-of-the-art language models (LMs) surpass most humans in certain domains, their reasoning remains largely opaque, reducing trust and increasing the risk of deception and hallucination.
By Yordan Yordanov, Matteo Forasassi, Bayar Menzat, Ruizhi Wang, Chang Qi, Markus Kaltenberger, Amine M'Charrak, Tommaso Salvatori, Thomas Lukasiewicz
arXiv:2606. 26620v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed language model representations into sparse and interpretable features.
By XinYang He, Wei Wang, Bing Zhao, Xuan Ren, WenBo Li, WeiXu Qiao, Hu Wei, Lin Qu
arXiv:2608. 07594v1 Announce Type: cross Abstract: Interpretability is often treated as a tax on capability: language models are trained as opaque systems, then explained after the fact, with methods whose reliability is difficult to establish.
By Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail, Giang Nguyen, Isaac Plant, Muawiz Chaudhary, Nathaniel Monson, Saqib Azim, Zhichen Guo, Julius Adebayo
Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on external observation. This reliance leads to superficial explanations inferred from observed model behavior and computational inefficiency from collecting such behavioral evidence at scale.
The paper introduces a method for identifying the dominant knowledge source behind large language model (LLM) outputs, distinguishing between faithfulness violations (misuse of provided context) and factuality violations (errors in internal knowledge). A simple linear probe trained on hidden representations can reliably classify this source, and the authors present AttriWiki, a self‑supervised pipeline that generates labeled training data by prompting models to recall withheld entities or read them from context. Probes trained on AttriWiki achieve high Macro‑F1 scores across several models and datasets, generalize zero‑shot to a benchmark, and show that attribution mismatches can increase error rates by up to 70%.
"whyItMatters":"The study demonstrates that knowing the source of an LLM’s answer is crucial for effective mitigation of hallucinations, as attribution mismatches significantly raise error rates."
By Ivo Brink, Alexander Boer, Dennis Ulmer
arXiv:2601. 22108v2 Announce Type: replace-cross Abstract: Continued pretraining is optimized with fixed self-supervised tasks but selected by downstream performance, creating a coarse feedback loop in which practitioners evaluate checkpoints, change data mixtures or objectives, and restart runs, while individual updates remain blind to target capabilities.
By Shuqi Ke, Giulia Fanti
arXiv:2607. 20652v1 Announce Type: cross Abstract: Language models are thought to exhibit the phenomenon of superposition, representing many more features than dimensions in their residual streams.
By Andrew Mack, Kraig Yuheng Tou, Mark Henry, Zhengxun Wu, Lauren Greenspan
arXiv:2603. 03031v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning.
By Xuan Yang, Jiayu Liu, Yuhang Lai, Hao Xu, Zhenya Huang, Ning Miao
arXiv:2608.30627v1 Announce Type: new
Abstract: As language-model compute continues to scale, high-quality training data is becoming an increasingly important bottleneck. Conventional next-token pred...
By Haoran Que, Jiajun Shi, Ting Huang, Renming Pang, Jiaheng Liu, Ge Zhang, Wenhao Huang, Shen Yan, Wei Ye, Shikun Zhang
arXiv:2605. 28969v2 Announce Type: replace-cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user.
By Aarik Gulaya
arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.
By Konstantinos P. Panousis, Diego Marcos