Investigating Syntactic Biases in Multilingual Transformers with RC Attachment Ambiguities in Italian and English

• URL: http://arxiv.org/abs/2504.09886v1
• Date: Mon, 14 Apr 2025 05:19:23 GMT
• Title: Investigating Syntactic Biases in Multilingual Transformers with RC Attachment Ambiguities in Italian and English
• Authors: Michael Kamerath, Aniello De Santo,
• Abstract summary: We investigate whether monolingual and multilingual LLMs show human-like preferences when presented with examples of relative clause attachment ambiguities in Italian and English.<n>We also test whether these preferences can be modulated by lexical factors which have been shown to be tied to subtle constraints on syntactic and semantic relations.
• Score: 1.2891210250935148
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper leverages past sentence processing studies to investigate whether monolingual and multilingual LLMs show human-like preferences when presented with examples of relative clause attachment ambiguities in Italian and English. Furthermore, we test whether these preferences can be modulated by lexical factors (the type of verb/noun in the matrix clause) which have been shown to be tied to subtle constraints on syntactic and semantic relations. Our results overall showcase how LLM behavior varies interestingly across models, but also general failings of these models in correctly capturing human-like preferences. In light of these results, we argue that RC attachment is the ideal benchmark for cross-linguistic investigations of LLMs' linguistic knowledge and biases.

Related papers

• Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions [26.87470552888266]
  Large Language Models (LLMs) have emerged as powerful sources of evidence for linguists seeking to develop theories of syntax.<n>This paper argues that causal interpretability methods, applied to LLMs, can greatly enhance the value of such evidence.
  arXiv  Detail & Related papers  (2025-05-21T20:37:57Z)
• Who Relies More on World Knowledge and Bias for Syntactic Ambiguity Resolution: Humans or LLMs? [2.3749120526936465]
  This study explores how recent large language models (LLMs) navigate relative clause attachment ambiguity in six typologically diverse languages.
  arXiv  Detail & Related papers  (2025-03-13T19:44:15Z)
• Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English [66.97110551643722]
  We investigate dialectal disparities in Large Language Models (LLMs) reasoning tasks.<n>We find that LLMs produce less accurate responses and simpler reasoning chains and explanations for AAE inputs.<n>These findings highlight systematic differences in how LLMs process and reason about different language varieties.
  arXiv  Detail & Related papers  (2025-03-06T05:15:34Z)
• Multilingual Relative Clause Attachment Ambiguity Resolution in Large Language Models [2.3749120526936465]
  Large language models (LLMs) resolve relative clause (RC) attachment ambiguities.<n>We assess whether LLMs can achieve human-like interpretations amid the complexities of language.<n>We evaluate models in English, Spanish, French, German, Japanese, and Korean.
  arXiv  Detail & Related papers  (2025-03-04T19:56:56Z)
• 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)
• 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)
• Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis [5.029635172046762]
  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.
  arXiv  Detail & Related papers  (2024-10-17T05:43:30Z)
• Evaluating the Correctness of Inference Patterns Used by LLMs for Judgment [53.17596274334017]
  We evaluate the correctness of the detailed inference patterns of an LLM behind its seemingly correct outputs.<n>Experiments show that even when the language generation results appear correct, a significant portion of the inference patterns used by the LLM for the legal judgment may represent misleading or irrelevant logic.
  arXiv  Detail & Related papers  (2024-10-06T08:33:39Z)
• 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)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrations [0.8133739801185272]
  We propose CrossAlpaca, an It-LLM with cross-lingual instruction-following and Translation-following demonstrations. Our models, tested over six different languages, outperform the It-LLMs tuned on monolingual data.
  arXiv  Detail & Related papers  (2023-08-27T19:22:12Z)
• Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds [59.71218039095155]
  We evaluate language understanding capacities on simple inference tasks that most humans find trivial. We target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments. The models exhibit moderate to low performance on these evaluation sets.
  arXiv  Detail & Related papers  (2023-05-24T06:41:09Z)
• Understanding Translationese in Cross-Lingual Summarization [106.69566000567598]
  Cross-lingual summarization (MS) aims at generating a concise summary in a different target language. To collect large-scale CLS data, existing datasets typically involve translation in their creation. In this paper, we first confirm that different approaches of constructing CLS datasets will lead to different degrees of translationese.
  arXiv  Detail & Related papers  (2022-12-14T13:41:49Z)
• Attribution Analysis of Grammatical Dependencies in LSTMs [0.043512163406551986]
  LSTM language models have been shown to capture syntax-sensitive grammatical dependencies with a high degree of accuracy. We show that LSTM performance on number agreement is directly correlated with the model's ability to distinguish subjects from other nouns. Our results suggest that LSTM language models are able to infer robust representations of syntactic dependencies.
  arXiv  Detail & Related papers  (2020-04-30T19:19:37Z)

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.