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 only one pair is fully interoperable, another is partially compatible, and the remaining 26 pairs fail across all alignment levels. Further experiments reveal that a globally trained communication interface can act as a severe negative‑transfer prior, but inherited interfaces never outperform fresh‑interface controls by the preregistered margin.
By Narcis Marincat
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
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
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. 04926v1 Announce Type: cross Abstract: How does the way information reaches a transformer -- as symbolic tokens, a clean per-factor "oracle" code, or an entangled perceptual vector -- shape whether it binds that information compositionally?
By Yoshiyuki Ootani
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. 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: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
arXiv:2502. 15543v4 Announce Type: replace-cross Abstract: Large language models (LLMs) integrated with retrieval-augmented generation (RAG) have improved factuality by grounding outputs in external evidence.
By Pengcheng Huang, Zhenghao Liu, Yukun Yan, Haiyan Zhao, Xiaoyuan Yi, Hao Chen, Zhiyuan Liu, Maosong Sun, Tong Xiao, Ge Yu, Chenyan Xiong
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