Natural Fingerprints of Large Language Models

• URL: http://arxiv.org/abs/2504.14871v1
• Date: Mon, 21 Apr 2025 05:48:52 GMT
• Title: Natural Fingerprints of Large Language Models
• Authors: Teppei Suzuki, Ryokan Ri, Sho Takase,
• Abstract summary: Large language models (LLMs) often exhibit biases in their outputs.<n>These range from overt issues, such as unfair responses, to subtler patterns that can reveal which model produced them.<n>We investigate the factors that give rise to identifiable characteristics in LLMs.
• Score: 36.221625684689414
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) often exhibit biases -- systematic deviations from expected norms -- in their outputs. These range from overt issues, such as unfair responses, to subtler patterns that can reveal which model produced them. We investigate the factors that give rise to identifiable characteristics in LLMs. Since LLMs model training data distribution, it is reasonable that differences in training data naturally lead to the characteristics. However, our findings reveal that even when LLMs are trained on the exact same data, it is still possible to distinguish the source model based on its generated text. We refer to these unintended, distinctive characteristics as natural fingerprints. By systematically controlling training conditions, we show that the natural fingerprints can emerge from subtle differences in the training process, such as parameter sizes, optimization settings, and even random seeds. We believe that understanding natural fingerprints offers new insights into the origins of unintended bias and ways for improving control over LLM behavior.

Related papers

• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [79.01538178959726]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence. We introduce a novel generative model that generates tokens on the basis of human interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• Unnatural Languages Are Not Bugs but Features for LLMs [92.8332103170009]
  Large Language Models (LLMs) have been observed to process non-human-readable text sequences, such as jailbreak prompts.<n>We present a systematic investigation challenging this perception, demonstrating that unnatural languages contain latent features usable by models.
  arXiv  Detail & Related papers  (2025-03-02T12:10:17Z)
• Deterministic or probabilistic? The psychology of LLMs as random number generators [0.0]
  Large Language Models (LLMs) have transformed text generation through inherently probabilistic context-aware mechanisms.<n>Our results reveal that, despite their transformers-based architecture, these models often exhibit deterministic responses when prompted for random numerical outputs.
  arXiv  Detail & Related papers  (2025-02-27T10:45:27Z)
• DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models [50.54264918467997]
  Pre-trained language models (PLMs) have achieved impressive results on various natural language processing tasks.<n>Recent research has revealed that these models often rely on superficial features and shortcuts instead of developing a genuine understanding of language.<n>We propose Divergence Based Regularization (DBR) to mitigate this shortcut learning behavior.
  arXiv  Detail & Related papers  (2025-02-25T16:44:10Z)
• Predicting the Performance of Black-box LLMs through Self-Queries [60.87193950962585]
  Large language models (LLMs) are increasingly relied on in AI systems, predicting when they make mistakes is crucial. In this paper, we extract features of LLMs in a black-box manner by using follow-up prompts and taking the probabilities of different responses as representations. We demonstrate that training a linear model on these low-dimensional representations produces reliable predictors of model performance at the instance level.
  arXiv  Detail & Related papers  (2025-01-02T22:26:54Z)
• Lost in Inference: Rediscovering the Role of Natural Language Inference for Large Language Models [36.983534612895156]
  In the recent past, a popular way of evaluating natural language understanding (NLU) was to consider a model's ability to perform natural language inference (NLI) tasks. This paper focuses on five different NLI benchmarks across six models of different scales. We investigate if they are able to discriminate models of different size and quality and how their accuracies develop during training.
  arXiv  Detail & Related papers  (2024-11-21T13:09:36Z)
• Distinguishing the Knowable from the Unknowable with Language Models [15.471748481627143]
  In the absence of ground-truth probabilities, we explore a setting where, in order to disentangle a given uncertainty, a significantly larger model stands in as a proxy for the ground truth. We show that small linear probes trained on the embeddings of frozen, pretrained models accurately predict when larger models will be more confident at the token level. We propose a fully unsupervised method that achieves non-trivial accuracy on the same task.
  arXiv  Detail & Related papers  (2024-02-05T22:22:49Z)
• HuRef: HUman-REadable Fingerprint for Large Language Models [44.9820558213721]
  HuRef is a human-readable fingerprint for large language models.<n>It uniquely identifies the base model without interfering with training or exposing model parameters to the public.
  arXiv  Detail & Related papers  (2023-12-08T05:01:47Z)
• Do pretrained Transformers Learn In-Context by Gradient Descent? [21.23795112800977]
  In this paper, we investigate the emergence of In-Context Learning (ICL) in language models pre-trained on natural data (LLaMa-7B) We find that ICL and Gradient Descent (GD) modify the output distribution of language models differently. These results indicate that emphthe equivalence between ICL and GD remains an open hypothesis and calls for further studies.
  arXiv  Detail & Related papers  (2023-10-12T17:32:09Z)
• Personality Traits in Large Language Models [42.31355340867784]
  Personality is a key factor determining the effectiveness of communication.<n>We present a novel and comprehensive psychometrically valid and reliable methodology for administering and validating personality tests on widely-used large language models.<n>We discuss the application and ethical implications of the measurement and shaping method, in particular regarding responsible AI.
  arXiv  Detail & Related papers  (2023-07-01T00:58:51Z)
• On the Transferability of Pre-trained Language Models: A Study from Artificial Datasets [74.11825654535895]
  Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance. We study what specific traits in the pre-training data, other than the semantics, make a pre-trained LM superior to their counterparts trained from scratch on downstream tasks.
  arXiv  Detail & Related papers  (2021-09-08T10:39:57Z)

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.