Fundamental Principles of Linguistic Structure are Not Represented by o3

• URL: http://arxiv.org/abs/2502.10934v1
• Date: Sat, 15 Feb 2025 23:53:31 GMT
• Title: Fundamental Principles of Linguistic Structure are Not Represented by o3
• Authors: Elliot Murphy, Evelina Leivada, Vittoria Dentella, Fritz Gunther, Gary Marcus,
• Abstract summary: o3 model fails to generalize basic phrase structure rules. It fails to correctly rate and explain acceptability dynamics. It fails to distinguish between instructions to generate unacceptable semantic vs. unacceptable syntactic outputs.
• Score: 3.335047764053173
• License:
• Abstract: A core component of a successful artificial general intelligence would be the rapid creation and manipulation of grounded compositional abstractions and the demonstration of expertise in the family of recursive hierarchical syntactic objects necessary for the creative use of human language. We evaluated the recently released o3 model (OpenAI; o3-mini-high) and discovered that while it succeeds on some basic linguistic tests relying on linear, surface statistics (e.g., the Strawberry Test), it fails to generalize basic phrase structure rules; it fails with comparative sentences involving semantically illegal cardinality comparisons ('Escher sentences'); its fails to correctly rate and explain acceptability dynamics; and it fails to distinguish between instructions to generate unacceptable semantic vs. unacceptable syntactic outputs. When tasked with generating simple violations of grammatical rules, it is seemingly incapable of representing multiple parses to evaluate against various possible semantic interpretations. In stark contrast to many recent claims that artificial language models are on the verge of replacing the field of linguistics, our results suggest not only that deep learning is hitting a wall with respect to compositionality (Marcus 2022), but that it is hitting [a [stubbornly [resilient wall]]] that cannot readily be surmounted to reach human-like compositional reasoning simply through more compute.

Related papers

• SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding [52.98133831401225]
  Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence. We propose a large language model-driven method for negative query construction, utilizing GPT-3.5-Turbo. We introduce a coarse-to-fine saliency ranking strategy, which encourages the model to learn the multi-granularity semantic relationships between videos and hierarchical negative queries.
  arXiv  Detail & Related papers  (2024-07-06T16:08:17Z)
• 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)
• Sentence Representation Learning with Generative Objective rather than Contrastive Objective [86.01683892956144]
  We propose a novel generative self-supervised learning objective based on phrase reconstruction. Our generative learning achieves powerful enough performance improvement and outperforms the current state-of-the-art contrastive methods.
  arXiv  Detail & Related papers  (2022-10-16T07:47:46Z)
• Idiomatic Expression Identification using Semantic Compatibility [8.355785779504869]
  We study the task of detecting whether a sentence has an idiomatic expression and localizing it. We propose a multi-stage neural architecture with the attention flow mechanism for identifying these expressions. A salient feature of the model is its ability to identify idioms unseen during training with gains from 1.4% to 30.8% over competitive baselines.
  arXiv  Detail & Related papers  (2021-10-19T15:44:28Z)
• Pairwise Supervised Contrastive Learning of Sentence Representations [20.822509446824125]
  PairSupCon aims to bridge semantic entailment and contradiction understanding with high-level categorical concept encoding. We evaluate it on various downstream tasks that involve understanding sentence semantics at different granularities.
  arXiv  Detail & Related papers  (2021-09-12T04:12:16Z)
• Neural Abstructions: Abstractions that Support Construction for Grounded Language Learning [69.1137074774244]
  Leveraging language interactions effectively requires addressing limitations in the two most common approaches to language grounding. We introduce the idea of neural abstructions: a set of constraints on the inference procedure of a label-conditioned generative model. We show that with this method a user population is able to build a semantic modification for an open-ended house task in Minecraft.
  arXiv  Detail & Related papers  (2021-07-20T07:01:15Z)
• Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand? [87.20342701232869]
  We investigate the abilities of ungrounded systems to acquire meaning. We study whether assertions enable a system to emulate representations preserving semantic relations like equivalence. We find that assertions enable semantic emulation if all expressions in the language are referentially transparent. However, if the language uses non-transparent patterns like variable binding, we show that emulation can become an uncomputable problem.
  arXiv  Detail & Related papers  (2021-04-22T01:00:17Z)
• Multi-sense embeddings through a word sense disambiguation process [2.2344764434954256]
  Most Suitable Sense. (MSSA) disambiguates and annotates each word by its specific sense, considering the semantic effects of its context. We test our approach on six different benchmarks for the word similarity task, showing that our approach can produce state-of-the-art results.
  arXiv  Detail & Related papers  (2021-01-21T16:22:34Z)
• Reevaluating Adversarial Examples in Natural Language [20.14869834829091]
  We analyze the outputs of two state-of-the-art synonym substitution attacks. We find that their perturbations often do not preserve semantics, and 38% introduce grammatical errors. With constraints adjusted to better preserve semantics and grammaticality, the attack success rate drops by over 70 percentage points.
  arXiv  Detail & Related papers  (2020-04-25T03:09:48Z)
• A Benchmark for Systematic Generalization in Grounded Language Understanding [61.432407738682635]
  Humans easily interpret expressions that describe unfamiliar situations composed from familiar parts. Modern neural networks, by contrast, struggle to interpret novel compositions. We introduce a new benchmark, gSCAN, for evaluating compositional generalization in situated language understanding.
  arXiv  Detail & Related papers  (2020-03-11T08:40:15Z)

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.