Lune

ACL Findings2026

Concept Tokens: Learning Behavioral Embeddings Through Concept Definitions

Ignacio Sastre, Aiala Rosá

Abstract

We propose Concept Tokens, a lightweight method that adds a new special token to a pretrained LLM and learns only its embedding from multiple natural language definitions of a target concept, where occurrences of the concept are replaced by the new token. The LLM is kept frozen and the embedding is optimized with the standard language-modeling objective. We evaluate Concept Tokens in three settings. First, we study hallucinations in closedbook question answering on HotpotQA and find a directional effect: negating the hallucination token reduces hallucinated answers mainly by increasing abstentions, whereas asserting it increases hallucinations and lowers precision. Second, we induce recasting, a pedagogical feedback strategy for second language teaching, and observe the same directional effect. Moreover, compared to providing the full definitional corpus in-context, concept tokens better preserve compliance with other instructions (e.g., asking follow-up questions). Finally, we include a qualitative study with the Eiffel Tower and a fictional "Austral Tower" to illustrate what information the learned embeddings capture and where their limitations emerge. Overall, Concept Tokens provide a compact control signal learned from definitions that can steer behavior in frozen LLMs. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Extracting Latent Steering Vectors from Pretrained Language Models cites The Power of Scale for Parameter-Efficient Prompt Tuning
  • 500xCompressor: Generalized Prompt Compression for Large Language Models cites The Power of Scale for Parameter-Efficient Prompt Tuning
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on7

  1. The Power of Scale for Parameter-Efficient Prompt TuningBrian Lester, Rami Al-Rfou, Noah ConstantEMNLP 2021 · 94 citations
  2. 500xCompressor: Generalized Prompt Compression for Large Language ModelsZongqian Li, Yixuan Su, Nigel CollierACL 2025 · 35 citations
  3. Extracting Latent Steering Vectors from Pretrained Language ModelsNishant Subramani, Nivedita Suresh, Matthew E. PetersACL Findings 2022 · 32 citations
  4. Controlling Large Language Models Through Concept Activation VectorsHanyu Zhang, Xiting Wang, Chengao Li, Xiang Ao et al.AAAI 2025 · 26 citations
  5. Toward Efficient Sparse Autoencoder-Guided Steering for Improved In-Context Learning in Large Language ModelsIkhyun Cho, Julia HockenmaierEMNLP 2025 · 3 citations

Related papers

  1. Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention LearningLei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan et al.ACL 2025
  2. DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language ModelsYung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim et al.ICLR 2024 · 354 citations
  3. SinkTrack: Attention Sink based Context Anchoring for Large Language ModelsXu Liu, Guikun Chen, Wenguan WangICLR 2026 · 4 citations
  4. SH2: Self-Highlighted Hesitation Helps You Decode More TruthfullyJushi Kai, Tianhang Zhang, Hai Hu, Zhouhan LinEMNLP Findings 2024 · 5 citations
  5. Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired DecodingWeixu Zhang, Fanghua Ye, Qiang Gao, Jian Li et al.ACL Findings 2026 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines