Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis

• URL: http://arxiv.org/abs/2410.13237v2
• Date: Sun, 09 Feb 2025 13:16:16 GMT
• Title: Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis
• Authors: Yiyi Chen, Qiongxiu Li, Russa Biswas, Johannes Bjerva,
• Abstract summary: Language Confusion is a phenomenon where Large Language Models (LLMs) generate text that is neither in the desired language, nor in a contextually appropriate language. We introduce a novel metric, Language Confusion Entropy, designed to measure and quantify this confusion.
• Score: 5.029635172046762
• License:
• Abstract: Language Confusion is a phenomenon where Large Language Models (LLMs) generate text that is neither in the desired language, nor in a contextually appropriate language. This phenomenon presents a critical challenge in text generation by LLMs, often appearing as erratic and unpredictable behavior. We hypothesize that there are linguistic regularities to this inherent vulnerability in LLMs and shed light on patterns of language confusion across LLMs. We introduce a novel metric, Language Confusion Entropy, designed to directly measure and quantify this confusion, based on language distributions informed by linguistic typology and lexical variation. Comprehensive comparisons with the Language Confusion Benchmark (Marchisio et al., 2024) confirm the effectiveness of our metric, revealing patterns of language confusion across LLMs. We further link language confusion to LLM security, and find patterns in the case of multilingual embedding inversion attacks. Our analysis demonstrates that linguistic typology offers theoretically grounded interpretation, and valuable insights into leveraging language similarities as a prior for LLM alignment and security.

Related papers

• Can Language Models Learn Typologically Implausible Languages? [62.823015163987996]
  Grammatical features across human languages show intriguing correlations often attributed to learning biases in humans. We discuss how language models (LMs) allow us to better determine the role of domain-general learning biases in language universals. 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)
• Randomly Sampled Language Reasoning Problems Reveal Limits of LLMs [8.146860674148044]
  We attempt to measure models' language understanding capacity while circumventing the risk of dataset recall. We parameterize large families of language tasks recognized by deterministic finite automata (DFAs) We find that, even in the strikingly simple setting of 3-state DFAs, LLMs underperform un parameterized ngram models on both language recognition and synthesis tasks.
  arXiv  Detail & Related papers  (2025-01-06T07:57:51Z)
• Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models [16.82812708514889]
  Code-switching, the phenomenon of alternating between two or more languages in a single conversation, presents unique challenges for Natural Language Processing (NLP) Most existing research focuses on either syntactic constraints or neural generation, with few efforts to integrate linguistic theory with large language models (LLMs) for generating natural code-switched text. We introduce EZSwitch, a novel framework that combines Equivalence Constraint Theory (ECT) with LLMs to produce linguistically valid and fluent code-switched text.
  arXiv  Detail & Related papers  (2024-10-30T03:03:32Z)
• Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs [13.558778781305998]
  Large Language Models (LLMs) are predominantly designed with English as the primary language. Even the few that are multilingual tend to exhibit strong English-centric biases. This paper introduces novel automatic corpus-level metrics to assess the lexical and syntactic naturalness of multilingual outputs.
  arXiv  Detail & Related papers  (2024-10-21T12:34:17Z)
• Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models [11.423589362950812]
  Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. Recent studies suggest that LLMs can transfer skills learned in one language to others, but the internal mechanisms behind this ability remain unclear. This paper provides insights into the internal workings of LLMs, offering a foundation for future improvements in their cross-lingual capabilities.
  arXiv  Detail & Related papers  (2024-10-15T15:49:15Z)
• Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
  We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts. We find that Llama Instruct and Mistral models exhibit high degrees of language confusion. 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)
• Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models [117.20416338476856]
  Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. We propose a novel detection method, language activation probability entropy (LAPE), to identify language-specific neurons within LLMs. Our findings indicate that LLMs' proficiency in processing a particular language is predominantly due to a small subset of neurons.
  arXiv  Detail & Related papers  (2024-02-26T09:36:05Z)
• How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering [52.86931192259096]
  Knowledge Base Question Answering (KBQA) aims to answer natural language questions based on facts in knowledge bases. Recent works leverage the capabilities of large language models (LLMs) for logical form generation to improve performance.
  arXiv  Detail & Related papers  (2024-01-11T09:27:50Z)
• Language models are not naysayers: An analysis of language models on negation benchmarks [58.32362243122714]
  We evaluate the ability of current-generation auto-regressive language models to handle negation. We show that LLMs have several limitations including insensitivity to the presence of negation, an inability to capture the lexical semantics of negation, and a failure to reason under negation.
  arXiv  Detail & Related papers  (2023-06-14T01:16:37Z)
• Shortcut Learning of Large Language Models in Natural Language Understanding [119.45683008451698]
  Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks. They might rely on dataset bias and artifacts as shortcuts for prediction. This has significantly affected their generalizability and adversarial robustness.
  arXiv  Detail & Related papers  (2022-08-25T03:51:39Z)

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.