Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
60 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
8 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses (2305.11662v3)

Published 19 May 2023 in cs.CL and cs.AI

Abstract: At the staggering pace with which the capabilities of LLMs are increasing, creating future-proof evaluation sets to assess their understanding becomes more and more challenging. In this paper, we propose a novel paradigm for evaluating LLMs which leverages the idea that correct world understanding should be consistent across different (Fregean) senses of the same meaning. Accordingly, we measure understanding not in terms of correctness but by evaluating consistency across multiple senses that are generated by the model itself. We showcase our approach by instantiating a test where the different senses are different languages, hence using multilingual self-consistency as a litmus test for the model's understanding and simultaneously addressing the important topic of multilinguality. Taking one of the latest versions of ChatGPT as our object of study, we evaluate multilingual consistency for two different tasks across three different languages. We show that its multilingual consistency is still lacking, and that its task and world understanding are thus not language-independent. As our approach does not require any static evaluation corpora in languages other than English, it can easily and cheaply be extended to different languages and tasks and could become an integral part of future benchmarking efforts.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Synthetic QA corpora generation with roundtrip consistency. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6168–6173, Florence, Italy. Association for Computational Linguistics.
  2. Akari Asai and Hannaneh Hajishirzi. 2020. Logic-guided data augmentation and regularization for consistent question answering. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5642–5650, Online. Association for Computational Linguistics.
  3. PIQA: Reasoning about physical commonsense in natural language. In Thirty-Fourth AAAI Conference on Artificial Intelligence.
  4. Can NLI models verify QA systems’ predictions? In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3841–3854, Punta Cana, Dominican Republic. Association for Computational Linguistics.
  5. BoolQ: Exploring the surprising difficulty of natural yes/no questions. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2924–2936, Minneapolis, Minnesota. Association for Computational Linguistics.
  6. XNLI: Evaluating cross-lingual sentence representations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2475–2485, Brussels, Belgium. Association for Computational Linguistics.
  7. Measuring and Improving Consistency in Pretrained Language Models. Transactions of the Association for Computational Linguistics, 9:1012–1031.
  8. Gottlob Frege. 1892. Über Sinn und Bedeutung ["On sense and reference"]. Zeitschrift für Philosophie und philosophische Kritik, 100(1):25–50.
  9. David Heineman. 2023. Rethinking reasoning evaluation with theories of intelligence.
  10. Measuring massive multitask language understanding. In International Conference on Learning Representations (ICLR).
  11. Understanding by understanding not: Modeling negation in language models. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1301–1312, Online. Association for Computational Linguistics.
  12. XTREME: A massively multilingual multi-task benchmark for evaluating cross-lingual generalisation. In Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 4411–4421. PMLR.
  13. State-of-the-art generalisation research in NLP: A taxonomy and review. arXiv, arXiv:2210.03050.
  14. BECEL: Benchmark for consistency evaluation of language models. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3680–3696, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
  15. Myeongjun Jang and Thomas Lukasiewicz. 2023. Consistency analysis of ChatGPT. arXiv, arXiv:2303.06273.
  16. Nora Kassner and Hinrich Schütze. 2020. Negated and misprimed probes for pretrained language models: Birds can talk, but cannot fly. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7811–7818, Online. Association for Computational Linguistics.
  17. BeliefBank: Adding memory to a pre-trained language model for a systematic notion of belief. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8849–8861, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  18. A logic-driven framework for consistency of neural models. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3924–3935, Hong Kong, China. Association for Computational Linguistics.
  19. XGLUE: A new benchmark datasetfor cross-lingual pre-training, understanding and generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6008–6018, Online. Association for Computational Linguistics.
  20. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.
  21. Sources of hallucination by large language models on inference tasks. arXiv, arXiv:2303.06273.
  22. Pasquale Minervini and Sebastian Riedel. 2018. Adversarially regularising neural NLI models to integrate logical background knowledge. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 65–74, Brussels, Belgium. Association for Computational Linguistics.
  23. Enhancing self-consistency and performance of pre-trained language models through natural language inference. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1754–1768, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  24. Melanie Mitchell and David C. Krakauer. 2023. The debate over understanding in AI’s large language models. Proceedings of the National Academy of Sciences, 120(13):e2215907120.
  25. Adversarial NLI: A new benchmark for natural language understanding. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4885–4901, Online. Association for Computational Linguistics.
  26. OpenAI. 2023. GPT-4 technical report. arXiv, arXiv:2303.08774.
  27. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics.
  28. XCOPA: A multilingual dataset for causal commonsense reasoning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2362–2376, Online. Association for Computational Linguistics.
  29. Matt Post. 2018. A call for clarity in reporting BLEU scores. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 186–191, Brussels, Belgium. Association for Computational Linguistics.
  30. AI and the everything in the whole wide world benchmark. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual.
  31. Machine reading, fast and slow: When do models “understand” language? In Proceedings of the 29th International Conference on Computational Linguistics, pages 78–93, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
  32. COMET-22: Unbabel-IST 2022 submission for the metrics shared task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 578–585, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
  33. Choice of plausible alternatives: An evaluation of commonsense causal reasoning. In 2011 AAAI Spring Symposium Series.
  34. XTREME-R: Towards more challenging and nuanced multilingual evaluation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10215–10245, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  35. Social IQa: Commonsense reasoning about social interactions. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4463–4473, Hong Kong, China. Association for Computational Linguistics.
  36. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. CoRR, abs/2206.04615.
  37. Llama 2: Open foundation and fine-tuned chat models. arXiv, arXiv:2307.09288.
  38. SuperGLUE: A stickier benchmark for general-purpose language understanding systems. In Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS), Red Hook, NY, USA. Curran Associates Inc.
  39. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 353–355, Brussels, Belgium. Association for Computational Linguistics.
  40. What if we simply swap the two text fragments? A straightforward yet effective way to test the robustness of methods to confounding signals in nature language inference tasks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 7136–7143.
  41. A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1112–1122, New Orleans, Louisiana. Association for Computational Linguistics.
  42. Ludwig Wittgenstein. 1953. Philosophical investigations. Philosophische Untersuchungen. Macmillan.
  43. PAWS-X: A cross-lingual adversarial dataset for paraphrase identification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3687–3692, Hong Kong, China. Association for Computational Linguistics.
  44. PAWS: Paraphrase adversaries from word scrambling. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1298–1308, Minneapolis, Minnesota. Association for Computational Linguistics.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Xenia Ohmer (7 papers)
  2. Elia Bruni (32 papers)
  3. Dieuwke Hupkes (49 papers)
Citations (10)
View on Semantic Scholar