Concept Training for Human-Aligned Language Models

• URL: http://arxiv.org/abs/2603.29123v1
• Date: Tue, 31 Mar 2026 01:20:03 GMT
• Title: Concept Training for Human-Aligned Language Models
• Abstract summary: Next-token prediction trains language models to predict a single continuation token at each step.<n>We explore a framework that instead predicts concepts, approximated as sets of semantically related tokens.<n>We show that models trained with concept supervision exhibit stronger alignment with human semantic similarity judgments.
• Score: 32.18350772329571
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The next-token prediction (NTP) objective trains language models to predict a single continuation token at each step. In natural language, however, a prefix can be continued in many valid ways, and even similar meanings may differ in surface form. For example, the sentence ``this website is safe to \underline{browse}'' could plausibly continue with words such as browse, search, visit, surf, or navigate. While standard NTP training treats these alternatives as mutually exclusive targets, we explore a framework that instead predicts concepts, approximated as sets of semantically related tokens. We show that models trained with concept supervision exhibit stronger alignment with human semantic similarity judgments on multiple lexical benchmarks. These gains are accompanied by lower perplexity on semantically meaningful words (definition in Section 3.1), and a modest increase in global token-level perplexity, reflecting a tradeoff between standard NTP optimization and concept-level supervision. Our results suggest that concept-level objectives can improve semantic alignment while maintaining competitive language modeling performance.

Related papers

• Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models [62.054835560934066]
  Next Concept Prediction is a generative pretraining paradigm built on top of Next Token Prediction.<n>Our model, ConceptLM, quantizes hidden states using Vector Quantization and constructs a concept vocabulary.<n>Results on 13 benchmarks show that NCP yields consistent performance gains over traditional token-level models.
  arXiv  Detail & Related papers  (2026-02-09T18:33:31Z)
• Beyond Tokens: Concept-Level Training Objectives for LLMs [27.252567251972028]
  Next-token prediction (NTP) operates at the textittoken level, treating deviations from a single reference continuation as errors.<n>We propose a shift from token-level to concept-level prediction, where concepts group multiple surface forms of the same idea.<n>We show that concept-aware models achieve lower perplexity, improved robustness under domain shift, and stronger performance than NTP-based models on diverse NLP benchmarks.
  arXiv  Detail & Related papers  (2026-01-16T21:35:11Z)
• Idea-Gated Transformers: Enforcing Semantic Coherence via Differentiable Vocabulary Pruning [0.40611352512781856]
  We introduce the Idea-Gated Transformer, a novel architecture that separates semantic planning from syntactic generation.<n>We propose a differentiable gating mechanism that suppresses semantically irrelevant tokens, effectively pruning the search space in real-time.
  arXiv  Detail & Related papers  (2025-12-03T01:17:07Z)
• From Bytes to Ideas: Language Modeling with Autoregressive U-Nets [49.16552366851748]
  Tokenization imposes a fixed granularity on the input text.<n>We introduce an autoregressive U-Net that learns to embed its own tokens as it trains.
  arXiv  Detail & Related papers  (2025-06-17T17:55:11Z)
• Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations [34.88156871518115]
  Next-token prediction (NTP) optimization leads language models to extract and organize semantic structure from text.<n>We demonstrate that concepts corresponding to larger singular values are learned earlier during training, yielding a natural semantic hierarchy.<n>This insight motivates orthant-based clustering, a method that combines concept signs to identify interpretable semantic categories.
  arXiv  Detail & Related papers  (2025-05-13T08:46:04Z)
• A General and Flexible Multi-concept Parsing Framework for Multilingual Semantic Matching [60.51839859852572]
  We propose to resolve the text into multi concepts for multilingual semantic matching to liberate the model from the reliance on NER models. We conduct comprehensive experiments on English datasets QQP and MRPC, and Chinese dataset Medical-SM.
  arXiv  Detail & Related papers  (2024-03-05T13:55:16Z)
• Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation [100.81837601210597]
  We propose Concept Curation (CoCu) to bridge the gap between visual and textual semantics in pre-training data. CoCu achieves superb zero-shot transfer performance and greatly boosts language-supervised segmentation baseline by a large margin.
  arXiv  Detail & Related papers  (2023-09-24T00:05:39Z)
• Multilingual Conceptual Coverage in Text-to-Image Models [98.80343331645626]
  "Conceptual Coverage Across Languages" (CoCo-CroLa) is a technique for benchmarking the degree to which any generative text-to-image system provides multilingual parity to its training language in terms of tangible nouns. For each model we can assess "conceptual coverage" of a given target language relative to a source language by comparing the population of images generated for a series of tangible nouns in the source language to the population of images generated for each noun under translation in the target language.
  arXiv  Detail & Related papers  (2023-06-02T17:59:09Z)
• Few-shot Subgoal Planning with Language Models [58.11102061150875]
  We show that language priors encoded in pre-trained language models allow us to infer fine-grained subgoal sequences. In contrast to recent methods which make strong assumptions about subgoal supervision, our experiments show that language models can infer detailed subgoal sequences without any fine-tuning.
  arXiv  Detail & Related papers  (2022-05-28T01:03:30Z)

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.