arXiv:2607. 20379v1 Announce Type: new Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it.
By Hiskias Dingeto
arXiv:2507. 02778v3 Announce Type: replace-cross Abstract: Although large language models (LLMs) have transformed AI, they still make errors and follow unproductive reasoning paths.
By Ken Tsui
The paper introduces Exemplar Partitioning (EP), an unsupervised technique that constructs interpretable feature dictionaries from large language model activations by clustering streamed activations into Voronoi regions defined by exemplars and their averages. EP allows comparison of dictionaries across layers, checkpoints, and architectures, and demonstrates utility in interpreting model behavior, tracking training dynamics, detecting hidden concepts, and enabling targeted interventions. Experiments on Gemma‑2‑2B and Llama‑3.1‑8B show EP can reveal how instruction tuning reorganizes harmful prompt activations, facilitate interventions that alter model responses, and achieve high concept‑detection performance while requiring far fewer construction tokens than comparable methods.
By Jessica Rumbelow
arXiv:2609.13308v1 Announce Type: cross
Abstract: A companion evaluation found that naming the target part in a manipulation prompt increased action accuracy by 0.32-0.63 across eight vision-language...
By Sarthak Sattigeri
arXiv:2609.00756v1 Announce Type: new
Abstract: The Mutual Reinforcement Effect (MRE) asks whether a fine, span-level and a coarse, document-level task help each other when one model handles both. We...
By Chengguang Gan, Yunhao Liang, Hanjun Wei, Qinghao Zhang, Shiwen Ni
arXiv:2608. 14252v1 Announce Type: new Abstract: Recent work suggests that some large language model representations have content or reference.
By Brett Reynolds