Pith. sign in

REVIEW 5 cited by

minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.13112 v1 pith:2BX4YSLB submitted 2022-03-24 cs.CL

Kanishka Misra This is my paper · ORCID
classification cs.CL
keywords miniconslevelrepresentationalanalysesapplybehaviorallanguagelibrary
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present minicons, an open source library that provides a standard API for researchers interested in conducting behavioral and representational analyses of transformer-based language models (LMs). Specifically, minicons enables researchers to apply analysis methods at two levels: (1) at the prediction level -- by providing functions to efficiently extract word/sentence level probabilities; and (2) at the representational level -- by also facilitating efficient extraction of word/phrase level vectors from one or more layers. In this paper, we describe the library and apply it to two motivating case studies: One focusing on the learning dynamics of the BERT architecture on relative grammatical judgments, and the other on benchmarking 23 different LMs on zero-shot abductive reasoning. minicons is available at https://github.com/kanishkamisra/minicons

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. VIP-MINGLE: A Corpus for Videoconference and In-Person Multimodal Interaction in Group Language Engagement

    cs.HC 2026-07 conditional novelty 7.0 of 10

    A paired within-subject multimodal corpus of 32 groups recorded in-person and via videoconference reveals setting-specific shifts in turn-taking, language complexity, facial expression, and rated enjoyment.

  2. Is It JUST Semantics? A Case Study of Discourse Particle Understanding in LLMs

    cs.CL 2025-06 conditional novelty 6.0 of 10

    LLMs separate broad senses of "just" such as temporal and adjective, but on naturalistic sentences they struggle to distinguish the fine-grained discourse-particle senses.

  3. Language Models Largely Exhibit Human-like Constituent Ordering Preferences

    cs.CL 2025-02 conditional novelty 6.0 of 10

    Across heavy NP shift, dative alternation and multiple PP shift, LLM ordering preferences correlate with human judgments, but particle movement preferences do not.

  4. Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora

    cs.CL 2024-12 conditional novelty 6.0 of 10

    A hybrid causal-masked language model won both text tracks of the BabyLM data-efficiency challenge, and no multimodal submission beat the baseline.

  5. semantic-features: A User-Friendly Tool for Studying Contextual Word Embeddings in Interpretable Semantic Spaces

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A library and demo reveal that masked language models encode the dative construction's person-like versus place-like reading of ambiguous recipients.

Pith tools