The paper argues that meaning identity—whether two sentences convey the same idea after wording changes—is not encoded in the geometry of independently produced sentence embeddings. Experiments on frozen off‑the‑shelf encoders and language models show that identity can only be reliably computed when both sentences are processed together in a single forward pass, yielding high accuracy (0.90–0.96) on PAWS‑X, whereas independent embeddings or simple fusion methods perform near chance. Even advanced bi‑encoder fine‑tuning improves performance on PAWS but fails to generalize to other similarity tasks, underscoring that identity is a cheap computed operator rather than a property of individual sentence vectors.
By Jiaqi Deng
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. 03598v1 Announce Type: cross Abstract: When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by sending it: share a finished project and it critiques the code; share a raw late-night line and it runs a wellness check.
By Alex Kwon
arXiv:2607. 06925v1 Announce Type: new Abstract: Compact world models that condition on a language goal promise to ground relations such as ``put the red block left of the blue block'' using a sparse set of explicit \emph{reference anchors}.
By Yufeng Wang, Lu Wei, Haibin Ling
arXiv:2608. 05687v1 Announce Type: cross Abstract: Masked diffusion language models (dLLMs) can commit tokens in any order -- a freedom marketed as their core advantage over autoregressive decoding.
By Jewon Yeom, Jaewon Sok, Seonghyeon Park, Jeongjae Park, Hwiyeong Lee, Taesup Kim
The paper demonstrates that a prompt’s influence is not inherent to the prompt itself but depends on the model, as prompts optimized for one model degrade on another and rankings shift under neutral reformatting. By examining a task‑free structural readout—specifically the fixed‑point behavior of a short‑window argmax map—the authors show that nine tokens of conditioning can move the fixed‑point fraction across most of its range, altering structural classes and model rankings, while instruction tuning has no effect. Attempts to explain this phenomenon through prefix length, content type, bidirectionality, or attention‑sink dominance all fail, indicating that the prompt‑model pair is the fundamental unit of explanation.
whyItMatters":"The study reveals that prompt effectiveness is model‑specific and that simple structural readouts can capture this interaction, challenging assumptions about prompt generality and guiding future prompt‑engineering efforts."
By Nicol\'as Vera Z\'u\~niga
arXiv:2607. 25532v1 Announce Type: new Abstract: Consider a model trained at a single hospital to predict patient recovery, where the measured feature $X$ bundles the patient's true health signal ($C$) with a systematic artefact from that hospital's equipment ($S$).
By Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz, Sotirios Tsaftaris
arXiv:2608. 15022v1 Announce Type: new Abstract: Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form when the task requires reusing it flexibly.
By Parsa Mazaheri
The paper investigates how the structural entanglement of facts within a large language model’s knowledge base influences whether those facts leak after unlearning. Using two unlearning algorithms (WHP and GA+KL) across fictional and real-world datasets and multiple model sizes, the authors find that highly entangled facts are more likely to be recalled before unlearning, but the relationship changes—WHP weakens it while GA+KL reverses it. By directly manipulating entanglement scores and observing corresponding recall changes, they demonstrate a causal link and develop a predictive tool to audit prompts for potential leakage.
By Aakriti Shah, Yifan Hu, Thai Le
arXiv:2608. 04021v1 Announce Type: cross Abstract: Cloze-style probes that vary how often a target token appears implicitly assume that more copies of a target affect prediction the same way regardless of where the readout slot sits.
By Han-yu Wang
arXiv:2609.14759v1 Announce Type: cross
Abstract: Alignment applied after pretraining is shallow in a measurable way: a single direction in a model's residual stream can be edited out, and the model...
By Orion Reblitz-Richardson
The study investigates how demographic identity is represented in a language model, using representational similarity analysis against Pew survey data across 169 demographic cells. It finds that standard last‑token read‑outs underestimate the model’s fidelity, while specific attention heads (notably L11 H16) capture demographic structure more accurately, though race‑based types remain weak. Causal interventions reveal that high fidelity does not guarantee causal use, and a 128‑dimensional probe of a single head improves alignment with survey truth but fails to recover per‑question group ordering.