LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages

• URL: http://arxiv.org/abs/2406.06196v3
• Date: Thu, 31 Oct 2024 10:14:49 GMT
• Title: LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages
• Authors: Andrew M. Bean, Simi Hellsten, Harry Mayne, Jabez Magomere, Ethan A. Chi, Ryan Chi, Scott A. Hale, Hannah Rose Kirk,
• Abstract summary: The LingOly benchmark is a novel benchmark for advanced reasoning abilities in large language models. We evaluate capabilities for in-context identification and generalisation of linguistic patterns in very low-resource or extinct languages. We assess performance with both direct accuracy and comparison to a no-context baseline to penalise memorisation.
• Score: 8.754506364968394
• License:
• Abstract: In this paper, we present the LingOly benchmark, a novel benchmark for advanced reasoning abilities in large language models. Using challenging Linguistic Olympiad puzzles, we evaluate (i) capabilities for in-context identification and generalisation of linguistic patterns in very low-resource or extinct languages, and (ii) abilities to follow complex task instructions. The LingOly benchmark covers more than 90 mostly low-resource languages, minimising issues of data contamination, and contains 1,133 problems across 6 formats and 5 levels of human difficulty. We assess performance with both direct accuracy and comparison to a no-context baseline to penalise memorisation. Scores from 11 state-of-the-art LLMs demonstrate the benchmark to be challenging, and models perform poorly on the higher difficulty problems. On harder problems, even the top model only achieved 38.7% accuracy, a 24.7% improvement over the no-context baseline. Large closed models typically outperform open models, and in general, the higher resource the language, the better the scores. These results indicate, in absence of memorisation, true multi-step out-of-domain reasoning remains a challenge for current language models.

Related papers

• Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models [63.31878920079154]
  We propose a benchmark specifically designed to assess large language models' mathematical reasoning at the Olympiad level. Unlike existing Olympiad-related benchmarks, our dataset focuses exclusively on mathematics. Our experimental results show that even the most advanced models, OpenAI o1-mini and OpenAI o1-preview, struggle with highly challenging Olympiad-level problems.
  arXiv  Detail & Related papers  (2024-10-10T14:39:33Z)
• Linguini: A benchmark for language-agnostic linguistic reasoning [37.73108306825993]
  We propose a new benchmark to measure a language model's linguistic reasoning skills without relying on pre-existing language-specific knowledge. The test covers 894 questions grouped in 160 problems across 75 (mostly) extremely low-resource languages. We find that while all analyzed models rank below 25% accuracy, there is a significant gap between open and closed models.
  arXiv  Detail & Related papers  (2024-09-18T16:51:02Z)
• modeLing: A Novel Dataset for Testing Linguistic Reasoning in Language Models [23.105555180223487]
  modeLing is a novel benchmark of Linguistics Olympiad-style puzzles which tests few-shot reasoning in AI systems. We evaluate several large open source language models and GPT on our benchmark.
  arXiv  Detail & Related papers  (2024-06-24T18:00:59Z)
• One Thousand and One Pairs: A "novel" challenge for long-context language models [56.60667988954638]
  NoCha is a dataset of 1,001 pairs of true and false claims about 67 fictional books. Our annotators confirm that the largest share of pairs in NoCha require global reasoning over the entire book to verify. On average, models perform much better on pairs that require only sentence-level retrieval vs. global reasoning.
  arXiv  Detail & Related papers  (2024-06-24T02:03:57Z)
• IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models [18.260317326787035]
  This paper introduces IrokoBench -- a human-translated benchmark dataset for 16 typologically-diverse low-resource African languages. We use IrokoBench to evaluate zero-shot, few-shot, and translate-test settings(where test sets are translated into English) across 10 open and four proprietary language models. We observe a significant performance gap between open and proprietary models, with the highest performing open model, Aya-101 only at 58% of the best-performing proprietary model GPT-4o performance.
  arXiv  Detail & Related papers  (2024-06-05T15:23:08Z)
• Language Models for Text Classification: Is In-Context Learning Enough? [54.869097980761595]
  Recent foundational language models have shown state-of-the-art performance in many NLP tasks in zero- and few-shot settings. An advantage of these models over more standard approaches is the ability to understand instructions written in natural language (prompts) This makes them suitable for addressing text classification problems for domains with limited amounts of annotated instances.
  arXiv  Detail & Related papers  (2024-03-26T12:47:39Z)
• LMentry: A Language Model Benchmark of Elementary Language Tasks [39.71352171304755]
  LMentry is a benchmark that focuses on a compact set of tasks that are trivial to humans. It provides insights into the capabilities and robustness of large language models.
  arXiv  Detail & Related papers  (2022-11-03T18:01:12Z)
• Making Large Language Models Better Reasoners with Step-Aware Verifier [49.16750018427259]
  DIVERSE (Diverse Verifier on Reasoning Step) is a novel approach that further enhances the reasoning capability of language models. We evaluate DIVERSE on the latest language model code-davinci and show that it achieves new state-of-the-art results on six of eight reasoning benchmarks.
  arXiv  Detail & Related papers  (2022-06-06T03:38:36Z)
• Few-shot Learning with Multilingual Language Models [66.49496434282564]
  We train multilingual autoregressive language models on a balanced corpus covering a diverse set of languages. Our largest model sets new state of the art in few-shot learning in more than 20 representative languages. We present a detailed analysis of where the model succeeds and fails, showing in particular that it enables cross-lingual in-context learning.
  arXiv  Detail & Related papers  (2021-12-20T16:52:35Z)
• Learning to Learn Morphological Inflection for Resource-Poor Languages [105.11499402984482]
  We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource source languages to learn a set of model parameters. Experiments with two model architectures on 29 target languages from 3 families show that our suggested approach outperforms all baselines.
  arXiv  Detail & Related papers  (2020-04-28T05:13:17Z)

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.