We're Afraid Language Models Aren't Modeling Ambiguity
- URL: http://arxiv.org/abs/2304.14399v2
- Date: Fri, 20 Oct 2023 05:46:14 GMT
- Title: We're Afraid Language Models Aren't Modeling Ambiguity
- Authors: Alisa Liu, Zhaofeng Wu, Julian Michael, Alane Suhr, Peter West,
Alexander Koller, Swabha Swayamdipta, Noah A. Smith, Yejin Choi
- Abstract summary: Managing ambiguity is a key part of human language understanding.
We characterize ambiguity in a sentence by its effect on entailment relations with another sentence.
We show that a multilabel NLI model can flag political claims in the wild that are misleading due to ambiguity.
- Score: 136.8068419824318
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Ambiguity is an intrinsic feature of natural language. Managing ambiguity is
a key part of human language understanding, allowing us to anticipate
misunderstanding as communicators and revise our interpretations as listeners.
As language models (LMs) are increasingly employed as dialogue interfaces and
writing aids, handling ambiguous language is critical to their success. We
characterize ambiguity in a sentence by its effect on entailment relations with
another sentence, and collect AmbiEnt, a linguist-annotated benchmark of 1,645
examples with diverse kinds of ambiguity. We design a suite of tests based on
AmbiEnt, presenting the first evaluation of pretrained LMs to recognize
ambiguity and disentangle possible meanings. We find that the task remains
extremely challenging, including for GPT-4, whose generated disambiguations are
considered correct only 32% of the time in human evaluation, compared to 90%
for disambiguations in our dataset. Finally, to illustrate the value of
ambiguity-sensitive tools, we show that a multilabel NLI model can flag
political claims in the wild that are misleading due to ambiguity. We encourage
the field to rediscover the importance of ambiguity for NLP.
Related papers
- Evaluating Contextualized Representations of (Spanish) Ambiguous Words: A New Lexical Resource and Empirical Analysis [2.2530496464901106]
We evaluate semantic representations of Spanish ambiguous nouns in context in a suite of Spanish-language monolingual and multilingual BERT-based models.
We find that various BERT-based LMs' contextualized semantic representations capture some variance in human judgments but fall short of the human benchmark.
arXiv Detail & Related papers (2024-06-20T18:58:11Z) - Análise de ambiguidade linguĂstica em modelos de linguagem de grande escala (LLMs) [0.35069196259739965]
Linguistic ambiguity continues to represent a significant challenge for natural language processing (NLP) systems.
Inspired by the recent success of instructional models like ChatGPT and Gemini, this study aims to analyze and discuss linguistic ambiguity within these models.
arXiv Detail & Related papers (2024-04-25T14:45:07Z) - Scope Ambiguities in Large Language Models [29.427341094882966]
We investigate how different versions of certain autoregressive language models treat scope ambiguous sentences.
We introduce novel datasets that contain a joint total of almost 1,000 unique scope-ambiguous sentences.
Using these datasets, we find evidence that several models are sensitive to the meaning ambiguity in these sentences.
arXiv Detail & Related papers (2024-04-05T18:01:02Z) - A Taxonomy of Ambiguity Types for NLP [53.10379645698917]
We propose a taxonomy of ambiguity types as seen in English to facilitate NLP analysis.
Our taxonomy can help make meaningful splits in language ambiguity data, allowing for more fine-grained assessments of both datasets and model performance.
arXiv Detail & Related papers (2024-03-21T01:47:22Z) - A Latent-Variable Model for Intrinsic Probing [93.62808331764072]
We propose a novel latent-variable formulation for constructing intrinsic probes.
We find empirical evidence that pre-trained representations develop a cross-lingually entangled notion of morphosyntax.
arXiv Detail & Related papers (2022-01-20T15:01:12Z) - 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) - AM2iCo: Evaluating Word Meaning in Context across Low-ResourceLanguages
with Adversarial Examples [51.048234591165155]
We present AM2iCo, Adversarial and Multilingual Meaning in Context.
It aims to faithfully assess the ability of state-of-the-art (SotA) representation models to understand the identity of word meaning in cross-lingual contexts.
Results reveal that current SotA pretrained encoders substantially lag behind human performance.
arXiv Detail & Related papers (2021-04-17T20:23:45Z) - Speakers Fill Lexical Semantic Gaps with Context [65.08205006886591]
We operationalise the lexical ambiguity of a word as the entropy of meanings it can take.
We find significant correlations between our estimate of ambiguity and the number of synonyms a word has in WordNet.
This suggests that, in the presence of ambiguity, speakers compensate by making contexts more informative.
arXiv Detail & Related papers (2020-10-05T17:19:10Z)
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.