Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Jan 201319922001200920172026
3 results for “antonyms”
Understanding How Model Size Affects Few-shot Instruction Promptingcs.CL

Study shows model size inversely affects few-shot instruction accuracy.

problem Understanding how model size impacts few-shot instruction prompting accuracy.
method Introduced DeltaWords dataset to evaluate model's ability to follow instructions.
result Model size inversely affects few-shot instruction accuracy, with larger models performing worse.
model sizefew-shot promptinginstruction followingDeltaWordsantonym selection
2022-12-04abs ↗pdf ↗
The Expressive Power of Word Embeddingscs.LG

We seek to better understand the difference in quality of the several publicly released embeddings. We propose several tasks that help to distinguish the characteristics of different embeddings. Our evaluation of sentiment polarity and synonym/antonym relations shows that embeddings are able to capture surprisingly nua…

2013-01-15abs ↗pdf ↗
Do Word Embeddings Really Understand Loughran-McDonald's Polarities?q-fin.ST

The paper analyzes word embeddings and their failure to distinguish polarized terms.

problem Word embeddings fail to correctly distinguish terms with opposite polarities.
method Mathematical analysis of word2vec model, synthetic corpus generation, empirical assessment.
result Word embeddings treat antonyms as frequentist synonyms, leading to mixed polarity terms.
word embeddingspolaritiesantonymsNLPfinancial news
2021-03-17abs ↗pdf ↗