10 papers · 1 filter
Relation Geometry in Semantic Space of Language Models
Zhihan Cao, Hiroaki Yamada, Simone Teufel +4
When it comes to generating vector representations of words, current language models are achieving high-quality results. However, what is not known is the extent to which knowledge…
Sycophancy Hides Linearly in the Attention Heads
Rifo Genadi, Munachiso Nwadike, Nurdaulet Mukhituly +3
We find that correct-to-incorrect sycophancy signals are most linearly separable within multi-head attention activations. Motivated by the linear representation hypothesis, we trai…
Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM
Seiya Ishikura, Hiroaki Yamada, Tatsuya Hiraoka +1
This study proposes augmenting dialog data with think-aloud utterances (TAUs) for modeling individual personalities in text chat by LLM. TAU is a verbalization of a speaker's thoug…
Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning
Nhi Hoai Doan, Tatsuya Hiraoka, Kentaro Inui
This paper investigates the relationship between large language models' (LLMs) ability to recognize repetitive input patterns and their performance on in-context learning (ICL). In…
Spelling-out is not Straightforward: LLMs' Capability of Tokenization from Token to Characters
Tatsuya Hiraoka, Kentaro Inui
Large language models (LLMs) can spell out tokens character by character with high accuracy, yet they struggle with more complex character-level tasks, such as identifying composit…
Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance
Shintaro Ozaki, Tatsuya Hiraoka, Hiroto Otake +8
Large Language Models (LLMs) are known to process information using a proficient internal language consistently, referred to as latent language, which may differ from the input or…
Number Representations in LLMs: A Computational Parallel to Human Perception
H. V. AlquBoj, Hilal AlQuabeh, Velibor Bojkovic +4
Humans are believed to perceive numbers on a logarithmic mental number line, where smaller values are represented with greater resolution than larger ones. This cognitive bias, sup…
RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles
Munachiso Nwadike, Zangir Iklassov, Toluwani Aremu +6
We introduce the concept of the self-referencing causal cycle (abbreviated RECALL) - a mechanism that enables large language models (LLMs) to bypass the limitations of unidirection…
Repetition Neurons: How Do Language Models Produce Repetitions?
Tatsuya Hiraoka, Kentaro Inui
This paper introduces repetition neurons, regarded as skill neurons responsible for the repetition problem in text generation tasks. These neurons are progressively activated more…
The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces
Ahmed Oumar El-Shangiti, Tatsuya Hiraoka, Hilal AlQuabeh +2
This paper investigates whether large language models (LLMs) utilize numerical attributes encoded in a low-dimensional subspace of the embedding space when answering questions invo…