Finding Fuzziness in Neural Network Models of Language Processing

Misra, Kanishka; Rayz, Julia Taylor

doi:10.1007/978-3-030-82099-2_25

Cited by 4 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the NLI models also captured this effect, likely because they are able to encode typicality relations and use these relations for generalization (Han et al, 2022; Misra et al, 2022). However, GPT-DaVinci and BART-MNLI failed to do so.…”

Section: Empirical Regularitiesmentioning

confidence: 99%

“…They also fail at replicating many of the other effects documented in the psychology and cognitive science literatures. This indicates that even though LLMs may possess the type of knowledge necessary for inductive reasoning, for example, knowledge of category membership relations (Misra et al, 2022), they do not possess the reasoning algorithms necessary to generate human-like behavior.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Inductive reasoning in minds and machines.

Bhatia

2023

Psychological Review

View full text Add to dashboard Cite

Induction-the ability to generalize from existing knowledge-is the cornerstone of intelligence. Cognitive models of human induction are largely limited to toy problems and cannot make quantitative predictions for the thousands of different induction arguments that have been studied by researchers, or to the countless induction arguments that could be encountered in everyday life. Leading large language models (LLMs) go beyond toy problems but fail to mimic observed patterns of human induction. In this article, we combine rich knowledge representations obtained from LLMs with theories of human inductive reasoning developed by cognitive psychologists. We show that this integrative approach can capture several benchmark empirical findings on human induction and generate human-like responses to natural language arguments with thousands of common categories and properties. These findings shed light on the cognitive mechanisms at play in human induction and show how existing theories in psychology and cognitive science can be integrated with new methods in artificial intelligence, to successfully model highlevel human cognition.

show abstract

Section: Empirical Regularitiesmentioning

confidence: 99%

mentioning

confidence: 99%

Inductive reasoning in minds and machines.

Bhatia

2023

Psychological Review

View full text Add to dashboard Cite

show abstract

“…If the model achieves a good performance, then one can infer that the LM representation encodes the target linguistic knowledge (Tenney et al, 2019a,b;Hewitt and Liang, 2019;Wu et al, 2020;Vulić et al, 2020;Sorodoc et al, 2020;Ettinger, 2020;Geiger et al, 2021;Koto et al, 2021;Chersoni et al, 2021a;Conia and Navigli, 2022;Kim and Linzen, 2020;Arps et al, 2022;Misra et al, 2022).…”

Section: Probing Linguistic Knowledge In Language Modelsmentioning

confidence: 99%

On Quick Kisses and How to Make Them Count: A Study on Event Construal in Light Verb Constructions with BERT

Liu,

Chersoni

2023

Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP

View full text Add to dashboard Cite

Psycholinguistic studies suggested that our mental perception of events depends not only on the lexical items used to describe them, but also on the syntactic structure of the event description. More specifically, it has been argued that light verb constructions affect the perception of duration in event construal, such that the same event in this type of constructions is perceived by humans as taking less time (to give a kiss takes a shorter time than to kiss).In our paper, we present two experiments with BERT using English stimuli from psycholinguistic studies to investigate the effects of the syntactic construction on event duration and event similarity. We show that i) the dimensions of BERT vectors encode a smaller value for duration for both punctive and durative events in count syntax, in line with human results; on the other hand, we also found that ii) BERT semantic similarity fails to capture the conceptual shift that durative events should undergo in count syntax.

show abstract

“…Large language models (LLMs) have attained an extraordinary ability to harness natural language for solving diverse problems (Devlin et al, 2018), often without the need for finetuning Sanh et al, 2021). Moreover, LLMs have demonstrated the capacity to excel at realworld problems, such as mathematics (Lewkowycz et al, 2022), scientific question answering (Sadat and Caragea, 2022), predicting brain responses (Schrimpf et al, 2021), and classifying proteins and chemical compounds (Taylor et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP

2023

View full text Add to dashboard Cite

As researchers achieve unprecedented technological breakthroughs in natural language processing, the need to understand the systems underlying these advances is more pertinent than ever. BlackboxNLP, now in its sixth iteration, has played an important role in bringing together scholars from a diverse range of backgrounds in order to rigorously study the behavior, representations, and computations of "black-box" neural network models. Our workshop showcases original, cutting-edge research on topics including but not limited to:• analysis of representations via probing and related techniques;• explanation methods such as feature attribution, free-text explanations, or structured explanations; • interdisciplinary methods (e.g., from neuroscience, cognitive science, computer vision, etc.); • interpretable architectures and neural network modules;• mechanistic interpretability and reverse engineering of neural computations; • open-source tools for analysis, visualization, and/or explanation; • opinions about the state of interpretability and explainable NLP; and • targeted evaluations using simplified or formal languages.The sixth BlackboxNLP workshop will be held in Singapore on December 7, 2023, hosted by the Conference on Empirical Methods in Natural Language Processing (EMNLP). 29 full papers and 17 non-archival extended abstracts were accepted for in-person and online presentations, from a total of 66 submissions. This year's workshop will also feature 19 papers on interpretability from the Findings of the ACL: EMNLP 2023, as well as two invited talks and a panel discussion with experts in the field.BlackboxNLP 2023 would not have been possible without the high-quality peer reviews submitted by our program committee, as well as the logistical assistance provided by the EMNLP organizing committee. We gratefully acknowledge financial support from our sponsors, Google and Apple. Our invited speakers, panelists, authors, and presenters have allowed us to put together an outstanding program for all participants to enjoy.Welcome to BlackboxNLP! We look forward to seeing you in Singapore and online.

show abstract

Finding Fuzziness in Neural Network Models of Language Processing

Cited by 4 publications

References 13 publications

Inductive reasoning in minds and machines.

Inductive reasoning in minds and machines.

On Quick Kisses and How to Make Them Count: A Study on Event Construal in Light Verb Constructions with BERT

Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP

Contact Info

Product

Resources

About