The Illusion of Control: Why Bare Classifier Inversion Silently Fails in Concept-Bottleneck Text Generation

• URL: http://arxiv.org/abs/2608.22956v1
• Date: Mon, 24 Aug 2026 08:21:10 GMT
• Title: The Illusion of Control: Why Bare Classifier Inversion Silently Fails in Concept-Bottleneck Text Generation
• Abstract summary: Concept-bottleneck controllable generation routes multi-attribute control through a low-dimensional concept code.<n>We study this problem in concept-bottleneck text generation under multi-axis compositional generalisation.
• Score: 0.30693357740321775
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Concept-bottleneck controllable generation routes multi-attribute control through a low-dimensional concept code that, at deployment, must be synthesised from a target attribute configuration. We study this problem in concept-bottleneck text generation under multi-axis compositional generalisation, comparing three ways to obtain the inference-time code: classifier inversion against the encoder heads, reference-text encoding, and a post-hoc label-conditioned prior. Since a concept code admits no direct LM-fluency term, regularising inversion must instead constrain the code toward the encoder's training distribution. We therefore test bare inversion and three regularised variants: label-agnostic and label-conditioned Mahalanobis penalties, and a conditional normalising-flow density baseline. Every inversion variant we test underperforms a simple post-hoc prior fitted to per-combination encoder means on the same checkpoints, across three backbone families spanning $124$M to $8$B parameters. The bare form of classifier inversion also silently collapses to chance, traceable to a directly measured off-manifold code. We validate this diagnosis on real-world benchmarks and under external evaluators, enabling fair comparison with published baselines.

Related papers

• Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach [58.15427952222424]
  General-purpose text embeddings are widely deployed for such tasks, but broad semantic similarity can place semantically similar yet task-distinct examples.<n>We introduce Prototype-Guided Contrastive Learning (PGCL), a prototype-guided geometric regularization module built on top of frozen text embeddings.
  arXiv  Detail & Related papers  (2026-08-15T13:19:25Z)
• TraceCoder: Explainable and Auditable Code Generation with Position-Key Snippet Versioning [0.0]
  We present a code generation concept that addresses shortcomings through three complementary mechanisms.<n>A relational snippet-history schema records, per repair event, the benchmark reference, round number, failure text, and explanation.<n>A browser-based visualisation tool renders this history as heat-mapped, hover-annotated source code.
  arXiv  Detail & Related papers  (2026-07-28T22:03:52Z)
• Principles of Concept Representation in Sentence Encoders [0.24828140397930876]
  A sentence encoder supports a concept only when its latent space admits a low-distortion realization of the corresponding semantic operator.<n>This framing predicts both where current encoders succeed and where they are structurally mismatched to their supervision.<n>We identify four principles. Fine-tuning recalibrates the latent geometry rather than expanding it.<n>We release two new evaluation: a DBpedia semantic-gap benchmark and a modifier-labeled datasets NP paraphrase suite.
  arXiv  Detail & Related papers  (2026-06-05T07:33:05Z)
• Inferring Code Correctness from Specification [0.0]
  Large language models (LLMs) have become integral to modern software development, enabling automated code generation at scale.<n>We propose TRAILS (Targeted Reasoning Agreement via Inputs and Specifications), an approach that grounds LLM reasoning with concrete (input, output) pairs.<n>We evaluate TRAILS on two datasets, LiveCodeBench and CoCoClaNeL, across three LLMs (Qwen3Coder-30B, Devstral-Small-24B, and Olmo3.1-Instruct), comparing against HoarePrompt and a Zero-Shot Chain-of-Thought baseline.
  arXiv  Detail & Related papers  (2026-05-28T12:04:51Z)
• Collapse-Free Prototype Readout Layer for Transformer Encoders [0.0]
  DDCL-Attention is a prototype-based readout layer for transformer encoders.<n>It produces compact token summaries at linear complexity in sequence length.<n>Same framework supports three uses: a final readout layer, a differentiable codebook extending VQ-VAE, and a hierarchical document compressor.
  arXiv  Detail & Related papers  (2026-04-04T20:23:21Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• Exploiting Discriminative Codebook Prior for Autoregressive Image Generation [54.14166700058777]
  token-based autoregressive image generation systems first tokenize images into sequences of token indices with a codebook, and then model these sequences in an autoregressive paradigm.<n>While autoregressive generative models are trained only on index values, the prior encoded in the codebook, which contains rich token similarity information, is not exploited.<n>Recent studies have attempted to incorporate this prior by performing naive k-means clustering on the tokens, helping to facilitate the training of generative models with a reduced codebook.<n>We propose the Discriminative Codebook Prior Extractor (DCPE) as an alternative to k-means
  arXiv  Detail & Related papers  (2025-08-14T15:00:00Z)
• Semi-DETR: Semi-Supervised Object Detection with Detection Transformers [105.45018934087076]
  We analyze the DETR-based framework on semi-supervised object detection (SSOD) We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector. Our method outperforms all state-of-the-art methods by clear margins.
  arXiv  Detail & Related papers  (2023-07-16T16:32:14Z)
• GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation [70.75100533512021]
  In this paper, we formulate the label uncertainty problem as the diversity of potentially plausible bounding boxes of objects. We propose GLENet, a generative framework adapted from conditional variational autoencoders, to model the one-to-many relationship between a typical 3D object and its potential ground-truth bounding boxes with latent variables. The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors.
  arXiv  Detail & Related papers  (2022-07-06T06:26:17Z)
• Autoencoding Variational Autoencoder [56.05008520271406]
  We study the implications of this behaviour on the learned representations and also the consequences of fixing it by introducing a notion of self consistency. We show that encoders trained with our self-consistency approach lead to representations that are robust (insensitive) to perturbations in the input introduced by adversarial attacks.
  arXiv  Detail & Related papers  (2020-12-07T14:16:14Z)

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.