mlsanityData to 14 Oct 2026

Plausibility Processing in Transformer Language Models: Focusing on the Role of Attention Heads in GPT

arXiv 2310.13824 ↗First posted 20 Oct 2023cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

The goal of this paper is to explore how Transformer language models process semantic knowledge, especially regarding the plausibility of noun-verb relations. First, I demonstrate GPT2 exhibits a higher degree of similarity with humans in plausibility processing compared to other Transformer language models. Next, I delve into how knowledge of plausibility is contained within attention heads of GPT2 and how these heads causally contribute to GPT2's plausibility processing ability. Through several experiments, it was found that: i) GPT2 has a number of attention heads that detect plausible noun-verb relationships; ii) these heads collectively contribute to the Transformer's ability to process plausibility, albeit to varying degrees; and iii) attention heads' individual performance in detecting plausibility does not necessarily correlate with how much they contribute to GPT2's plausibility processing ability.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 20 Oct 2023.

Builds on

23 of 36 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  5. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  6. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  7. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 1,003
  8. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 856
  9. 2019Are Sixteen Heads Really Better than One?cited by 816
  10. 2019What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language modelscited by 320
  11. 2019A Multiscale Visualization of Attention in the Transformer Modelcited by 292
  12. 2018Analysis Methods in Neural Language Processing: A Surveycited by 277
11 more
  1. 2019Analyzing the Structure of Attention in a Transformer Language Modelcited by 243
  2. 2020Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Biascited by 191
  3. 2019Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic Statecited by 138
  4. 2020On the Predictive Power of Neural Language Models for Human Real-Time Comprehension Behaviorcited by 119
  5. 2018What do RNN Language Models Learn about Filler-Gap Dependencies?cited by 86
  6. 2020Human Sentence Processing: Recurrence or Attention?cited by 51
  7. 2020Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Primingcited by 41
  8. 2021Do language models learn typicality judgments from text?cited by 32
  9. 2021Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attentioncited by 27
  10. 2020How well does surprisal explain N400 amplitude under different experimental conditions?cited by 18
  11. 2021Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledgecited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ContiguousKV: Accelerating LLM Prefill with Granularity-Aligned KV Cache Managementcited by 1