The study investigates whether independently trained language‑model societies share a common packet language and how inherited interface states affect learning. A comprehensive audit of 30 pairwise interactions among six restricted societies shows that most cross‑initialization pairs fail to interoperate, with only one pair achieving full bidirectional compatibility. Further experiments reveal that reinitializing only the packet reader, writer, and mouth dramatically improves accuracy, while inherited interfaces never outperform fresh ones by the preregistered margin.
arXiv:2608. 20054v1 Announce Type: new Abstract: Multi-module systems often expose every module to the full input.
By Narcis Marincat
arXiv:2607.27617v2 Announce Type: replace
Abstract: Identical language-model answers can arise from hidden states that support different future computations, so current-answer probes do not establish...
By SiYuan Ma, Yiqin Luo, Zhangji, Canran Xiao, Albert Gao, Wei Wang, Qiwei Wu, Xinran Li, Jinfeng Wei, Qixin Zhang
arXiv:2608.20054v3 Announce Type: replace
Abstract: Multi-module neural systems often expose every module to the full input. We test whether a slot-selective evidence-masking regime -- restricting ea...
By Narcis Marincat
The study investigates whether restricting a module’s access to information—through evidence masking—enhances a system’s ability to learn compositional tasks. In a preregistered experiment with sixty‑four‑cell systems built on a frozen language‑model backbone, researchers varied evidence masking, ownership markers, and filler replacement across multiple initialization clusters and data orders. Results showed that when markers were available, masking significantly improved accuracy on held‑out two‑ and three‑operation compositions, with all tested pairs meeting performance thresholds and the preregistered behavioral criterion satisfied. The study also explored packet interventions and found predicted intermediate‑value changes, though mediation was not conclusively established.
"whyItMatters":"The findings demonstrate a substantial performance benefit from evidence masking in compositional generalization tasks, offering a promising direction for designing more effective learning systems."
By Narcis Marincat
arXiv:2607. 20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption.
By Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz
arXiv:2608. 16347v1 Announce Type: cross Abstract: Direct communication between AI systems relies on natural language as an intermediate layer, incurring encoding/decoding overhead, token cost, and latency.
By Fernando Cardenas Piepereit
arXiv:2605. 07284v2 Announce Type: replace Abstract: A late-layer change learned during post-training may work on the base model's earlier state, or it may depend on earlier computation learned with it.
By Yifan Zhou
arXiv:2608. 14465v1 Announce Type: cross Abstract: A frozen language model on reasoning tasks has two coupled weaknesses: it under-uses evidence its own residual stream already encodes, and it fails to detect when the input is insufficient to answer, so it confabulates.
By Ziyang Luo, Zhongyao Chu, Xinjie He, Youting Wang, Xukui Qin, Runxiong Wu, Yan-Syuan Chen
The paper investigates how new concepts can be integrated into unified multimodal models (UMMs) by separating generation and understanding objectives through a novel visual entity bound to a single task direction. Experiments show that the effectiveness of cross‑task usability depends on where the concept is injected into the shared computation, with a mid‑stack alignment objective achieving high concept acquisition with minimal loss to overall performance. The study highlights that unified weights alone are insufficient; the two directions must share a semantic format at the entry point for efficient concept integration.
By Zongyang Qiu, Yihan Wu, Kaixuan Fan, Bo Li, Hui Xiong
arXiv:2607. 29484v1 Announce Type: cross Abstract: Interventional data is widely regarded as the gold standard for teaching models causal reasoning.
By Xining Xun
arXiv:2607. 26929v1 Announce Type: cross Abstract: The same diagnostic result can support or challenge one causal claim yet fail to address another when the claims concern different populations, outcomes, estimands, pathways, or identifying assumptions.
By Weiyi Kong, Zhuoran Li