Biasless Language Models Learn Unnaturally: How LLMs Fail to Distinguish the Possible from the Impossible

• URL: http://arxiv.org/abs/2510.07178v1
• Date: Wed, 08 Oct 2025 16:17:13 GMT
• Title: Biasless Language Models Learn Unnaturally: How LLMs Fail to Distinguish the Possible from the Impossible
• Authors: Imry Ziv, Nur Lan, Emmanuel Chemla, Roni Katzir,
• Abstract summary: We show that GPT-2 learns each language and its impossible counterpart equally easily.<n>By considering cross-linguistic variance in various metrics computed on the perplexity curves, we show that GPT-2 provides no systematic separation between the possible and the impossible.
• Score: 4.7831562043724665
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Are large language models (LLMs) sensitive to the distinction between humanly possible languages and humanly impossible languages? This question is taken by many to bear on whether LLMs and humans share the same innate learning biases. Previous work has attempted to answer it in the positive by comparing LLM learning curves on existing language datasets and on "impossible" datasets derived from them via various perturbation functions. Using the same methodology, we examine this claim on a wider set of languages and impossible perturbations. We find that in most cases, GPT-2 learns each language and its impossible counterpart equally easily, in contrast to previous claims. We also apply a more lenient condition by testing whether GPT-2 provides any kind of separation between the whole set of natural languages and the whole set of impossible languages. By considering cross-linguistic variance in various metrics computed on the perplexity curves, we show that GPT-2 provides no systematic separation between the possible and the impossible. Taken together, these perspectives show that LLMs do not share the human innate biases that shape linguistic typology.

Related papers

• Language models as tools for investigating the distinction between possible and impossible natural languages [30.440694754088934]
  We argue that language models (LMs) have strong potential as investigative tools for probing the distinction between possible and impossible natural languages.<n>We outline a phased research program in which LM architectures are iteratively refined to better discriminate between possible and impossible languages.
  arXiv  Detail & Related papers  (2025-12-10T07:37:43Z)
• 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)
• Anything Goes? A Crosslinguistic Study of (Im)possible Language Learning in LMs [14.78046527879077]
  We train language models to model impossible and typologically unattested languages.<n>Our results show that while GPT-2 small can largely distinguish attested languages, it does not achieve perfect separation between all the attested languages and all the impossible ones.<n>These findings suggest that LMs exhibit some human-like inductive biases, though these biases are weaker than those found in human learners.
  arXiv  Detail & Related papers  (2025-02-26T04:01:36Z)
• Can Language Models Learn Typologically Implausible Languages? [62.823015163987996]
  Grammatical features across human languages show intriguing correlations often attributed to learning biases in humans.<n>We discuss how language models (LMs) allow us to better determine the role of domain-general learning biases in language universals.<n>We test LMs on an array of highly naturalistic but counterfactual versions of the English (head-initial) and Japanese (head-final) languages.
  arXiv  Detail & Related papers  (2025-02-17T20:40:01Z)
• Kallini et al. (2024) do not compare impossible languages with constituency-based ones [0.0]
  A central goal of linguistic theory is to find a characterization of the notion "possible human language" Recent large language models (LLMs) in NLP applications arguably raises the possibility that LLMs might be computational devices that meet this goal. I explain the confound and suggest some ways forward towards constructing a comparison that appropriately tests the underlying issue.
  arXiv  Detail & Related papers  (2024-10-16T06:16:30Z)
• Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
  We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts.<n>We find that Llama Instruct and Mistral models exhibit high degrees of language confusion.<n>We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
  arXiv  Detail & Related papers  (2024-06-28T17:03:51Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora.<n>But can these models relate corresponding concepts across languages, i.e., be crosslingual?<n>This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages [78.1866280652834]
  Large language models (LM) are distributions over strings.<n>We investigate the learnability of regular LMs (RLMs) by RNN and Transformer LMs.<n>We find that the complexity of the RLM rank is strong and significant predictors of learnability for both RNNs and Transformers.
  arXiv  Detail & Related papers  (2024-06-06T17:34:24Z)
• Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners [67.85635044939836]
  Large Language Models (LLMs) have shown impressive language capabilities. In this work, we investigate the spontaneous multilingual alignment improvement of LLMs. We find that LLMs instruction-tuned on the question translation data (i.e. without annotated answers) are able to encourage the alignment between English and a wide range of languages.
  arXiv  Detail & Related papers  (2024-05-22T16:46:19Z)
• Mission: Impossible Language Models [29.249131112359503]
  We develop a set of synthetic impossible languages of differing complexity. At one end are languages that are inherently impossible, such as random and irreversible shuffles of English words. At the other end are languages that may not be intuitively impossible but are often considered so in linguistics.
  arXiv  Detail & Related papers  (2024-01-12T07:24:26Z)

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.