Instruction-tuning Aligns LLMs to the Human Brain
- URL: http://arxiv.org/abs/2312.00575v1
- Date: Fri, 1 Dec 2023 13:31:02 GMT
- Title: Instruction-tuning Aligns LLMs to the Human Brain
- Authors: Khai Loong Aw, Syrielle Montariol, Badr AlKhamissi, Martin Schrimpf,
Antoine Bosselut
- Abstract summary: Instruction-tuning enables large language models to generate output that more closely resembles human responses to natural language queries.
We investigate whether instruction-tuning makes large language models more similar to how humans process language.
We find that instruction-tuning generally enhances brain alignment by an average of 6%, but does not have a similar effect on behavioral alignment.
- Score: 20.86703074354748
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Instruction-tuning is a widely adopted method of finetuning that enables
large language models (LLMs) to generate output that more closely resembles
human responses to natural language queries, in many cases leading to
human-level performance on diverse testbeds. However, it remains unclear
whether instruction-tuning truly makes LLMs more similar to how humans process
language. We investigate the effect of instruction-tuning on LLM-human
similarity in two ways: (1) brain alignment, the similarity of LLM internal
representations to neural activity in the human language system, and (2)
behavioral alignment, the similarity of LLM and human behavior on a reading
task. We assess 25 vanilla and instruction-tuned LLMs across three datasets
involving humans reading naturalistic stories and sentences. We discover that
instruction-tuning generally enhances brain alignment by an average of 6%, but
does not have a similar effect on behavioral alignment. To identify the factors
underlying LLM-brain alignment, we compute correlations between the brain
alignment of LLMs and various model properties, such as model size, various
problem-solving abilities, and performance on tasks requiring world knowledge
spanning various domains. Notably, we find a strong positive correlation
between brain alignment and model size (r = 0.95), as well as performance on
tasks requiring world knowledge (r = 0.81). Our results demonstrate that
instruction-tuning LLMs improves both world knowledge representations and brain
alignment, suggesting that mechanisms that encode world knowledge in LLMs also
improve representational alignment to the human brain.
Related papers
- Lost in Translation: The Algorithmic Gap Between LMs and the Brain [8.799971499357499]
Language Models (LMs) have achieved impressive performance on various linguistic tasks, but their relationship to human language processing in the brain remains unclear.
This paper examines the gaps and overlaps between LMs and the brain at different levels of analysis.
We discuss how insights from neuroscience, such as sparsity, modularity, internal states, and interactive learning, can inform the development of more biologically plausible language models.
arXiv Detail & Related papers (2024-07-05T17:43:16Z) - What Are Large Language Models Mapping to in the Brain? A Case Against Over-Reliance on Brain Scores [1.8175282137722093]
Internal representations from large language models (LLMs) achieve state-of-the-art brain scores, leading to speculation that they share computational principles with human language processing.
Here, we analyze three neural datasets used in an impactful study on LLM-to-brain mappings, with a particular focus on an fMRI dataset where participants read short passages.
We find that brain scores of trained LLMs on this dataset can largely be explained by sentence length, position, and pronoun-dereferenced static word embeddings.
arXiv Detail & Related papers (2024-06-03T17:13:27Z) - FAC$^2$E: Better Understanding Large Language Model Capabilities by
Dissociating Language and Cognition [57.747888532651]
Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks.
We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
arXiv Detail & Related papers (2024-02-29T21:05:37Z) - Characterizing Truthfulness in Large Language Model Generations with
Local Intrinsic Dimension [63.330262740414646]
We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs)
We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
arXiv Detail & Related papers (2024-02-28T04:56:21Z) - Do Large Language Models Mirror Cognitive Language Processing? [43.68923267228057]
Large Language Models (LLMs) have demonstrated remarkable abilities in text comprehension and logical reasoning.
In cognitive science, brain cognitive processing signals are typically utilized to study human language processing.
We employ Representational Similarity Analysis (RSA) to measure the alignment between 23 mainstream LLMs and fMRI signals of the brain.
arXiv Detail & Related papers (2024-02-28T03:38:20Z) - Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? [140.9751389452011]
We study the biases of large language models (LLMs) in relation to those known in children when solving arithmetic word problems.
We generate a novel set of word problems for each of these tests, using a neuro-symbolic approach that enables fine-grained control over the problem features.
arXiv Detail & Related papers (2024-01-31T18:48:20Z) - Contextual Feature Extraction Hierarchies Converge in Large Language
Models and the Brain [12.92793034617015]
We show that as large language models (LLMs) achieve higher performance on benchmark tasks, they become more brain-like.
We also show the importance of contextual information in improving model performance and brain similarity.
arXiv Detail & Related papers (2024-01-31T08:48:35Z) - Divergences between Language Models and Human Brains [63.405788999891335]
Recent research has hinted that brain signals can be effectively predicted using internal representations of language models (LMs)
We show that there are clear differences in how LMs and humans represent and use language.
We identify two domains that are not captured well by LMs: social/emotional intelligence and physical commonsense.
arXiv Detail & Related papers (2023-11-15T19:02:40Z) - Can Large Language Models Transform Computational Social Science? [79.62471267510963]
Large Language Models (LLMs) are capable of performing many language processing tasks zero-shot (without training data)
This work provides a road map for using LLMs as Computational Social Science tools.
arXiv Detail & Related papers (2023-04-12T17:33:28Z)
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.