They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It

• URL: http://arxiv.org/abs/2607.03598v1
• Date: Fri, 03 Jul 2026 20:49:37 GMT
• Title: They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It
• Abstract summary: We show that the failure of a language model to decode the sender's intent is one of readouts on top of a robust representation.<n>A linear probe decodes the sender's intent, whether they want a thing recognized or evaluated, across six models and four families and in the base checkpoints.<n>The behavioral half of the story is established on the recognize/evaluate contrast, where what varies is whether the default output acts on the intent.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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. We treat the sender's communicative intent, the Gricean what-was-meant, as a first-class interpretability object, and show the failure is one of readout on top of a robust representation. A linear probe decodes the sender's intent, whether they want a thing recognized or evaluated, from a model's default-pass hidden states, cleanly and surface-independently, across six models and four families and in the base checkpoints. The representation generalizes further, to intent that is only pragmatically inferred, and to a second, lexically clean intent (support versus help). The behavioral half of the story, and every causal test, is established on the recognize/evaluate contrast, where what varies is whether the default output acts on the intent. The readout lags the representation in depth within a model (the intent is decodable several layers before it drives the output); across models, which ones act on it by default is model-specific, an observed stratification (three of six show the failure) that we do not read as a scaling law. Where the gap is open, a direction closely tied to the representation, the discriminative direction at a searched-for layer, is a causal handle: steering it recovers the intended behavior, as well as an explicit instruction does and with no prompt at all. This direction is near-orthogonal to the feedback-offering axis, so it routes a represented intent rather than a generic feedback knob, though at the recovery dose the routed intent can override an explicit request. We support each link with controls against obvious deflations and report the nulls as plainly as the confirmations.

Related papers

• SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks [69.08780911753102]
  Multi-turn jailbreaks exploit a pattern by advancing a harmful intent across turns, so that no single message exposes the full objective.<n>We develop a four-part, intent-oriented taxonomy that organizes multi-turn jailbreaks by adversarial intent structure.
  arXiv  Detail & Related papers  (2026-08-02T09:24:08Z)
• Implicit Reasoning Steering via Concept Chaining [29.121206944212556]
  We use natural-language text to bias a model toward a designated answer without explicit instructions, triggers, or direct answer cues.<n>We show that indirect, natural-looking text can systematically steer model predictions while remaining substantially less inferable than direct paraphrases.
  arXiv  Detail & Related papers  (2026-07-15T18:03:08Z)
• Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs [41.451167369762544]
  We document a Representation-Action Gap: hidden states reliably encode premise-perception mismatches.<n> Behaviorally, models fall into two failure modes: under-rejection and over-rejection.<n>As an initial diagnostic intervention, a probe-guided logit adjustment re-injects the encoded mismatch signal into decoding.
  arXiv  Detail & Related papers  (2026-05-13T16:14:44Z)
• Pando: Do Interpretability Methods Work When Models Won't Explain Themselves? [53.07826484214082]
  We introduce Pando, a model-organism benchmark that breaks this confound via an explanation axis.<n>Pando predicts held-out model decisions from $10$ labeled query-response pairs.<n>When explanations are faithful, black-box elicitation matches or exceeds all white-box methods.
  arXiv  Detail & Related papers  (2026-04-13T06:42:24Z)
• Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails [0.0]
  We study political censorship in Chinese-origin language models as a natural experiment.<n>We use probes, surgical ablations, and behavioral tests across nine open-weight models from five labs.
  arXiv  Detail & Related papers  (2026-03-18T20:54:34Z)
• CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding [56.30142869506262]
  Embodied Reference Understanding involves predicting the object that a person in the scene is referring to through both pointing gesture and language.<n>We propose a dual-model framework, where one model learns from the head-to-fingertip direction and the other from the wrist-to-fingertip direction.<n>We validate our approach through extensive experiments and analysis on the benchmark YouRefIt dataset, achieving an improvement of approximately 4 mAP at the 0.25 IoU threshold.
  arXiv  Detail & Related papers  (2025-07-29T15:00:21Z)
• BURN: Backdoor Unlearning via Adversarial Boundary Analysis [73.14147934175604]
  Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality.<n>We propose Backdoor Unlearning via adversaRial bouNdary analysis (BURN), a novel defense framework that integrates false correlation decoupling, progressive data refinement, and model purification.
  arXiv  Detail & Related papers  (2025-07-14T17:13:06Z)
• The Geometry of Self-Verification in a Task-Specific Reasoning Model [45.669264589017665]
  We train a model using DeepSeek R1's recipe on the CountDown task.<n>We do top-down and bottom-up analyses to reverse-engineer how the model verifies its outputs.
  arXiv  Detail & Related papers  (2025-04-19T18:40:51Z)
• Exploring the Individuality and Collectivity of Intents behind Interactions for Graph Collaborative Filtering [9.740376003100437]
  We propose a novel recommendation framework designated as Bilateral Intent-guided Graph Collaborative Filtering (BIGCF) Specifically, we take a closer look at user-item interactions from a causal perspective and put forth the concepts of individual intent. To counter the sparsity of implicit feedback, the feature distributions of users and items are encoded via a Gaussian-based graph generation strategy.
  arXiv  Detail & Related papers  (2024-05-15T02:31:26Z)
• What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary [68.77983831618685]
  We propose to interpret the vector representations produced by dual encoders by projecting them into the model's vocabulary space. We show that the resulting projections contain rich semantic information, and draw connection between them and sparse retrieval.
  arXiv  Detail & Related papers  (2022-12-20T16:03:25Z)
• Contrastive Explanations for Model Interpretability [77.92370750072831]
  We propose a methodology to produce contrastive explanations for classification models. Our method is based on projecting model representation to a latent space. Our findings shed light on the ability of label-contrastive explanations to provide a more accurate and finer-grained interpretability of a model's decision.
  arXiv  Detail & Related papers  (2021-03-02T00:36:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.