Search Results for author:
Found 7 papers, 7 papers with code
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
We outperform encoder-only models by a large margin on word-level tasks and reach a new unsupervised state-of-the-art performance on the Massive Text Embeddings Benchmark (MTEB).
Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering
Guided by human evaluation and analysis, we highlight the shortcomings of traditional metrics for both correctness and faithfulness.
Image Retrieval from Contextual Descriptions
In particular, models are tasked with retrieving the correct image from a set of 10 minimally contrastive candidates based on a contextual description.
Ranked #1 on
Image Retrieval
on ImageCoDe
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
The principle is that this should result in worse model performance compared to masking random tokens.
TopiOCQA: Open-domain Conversational Question Answering with Topic Switching
On average, a conversation in our dataset spans 13 question-answer turns and involves four topics (documents).
OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction
This IGL based coordination analyzer helps our OpenIE system handle complicated coordination structures, while also establishing a new state of the art on the task of coordination analysis, with a 12. 3 pts improvement in F1 over previous analyzers.
Ranked #1 on
Open Information Extraction
on WiRe57
Regex Queries over Incomplete Knowledge Bases
In response, we develop RotatE-Box -- a novel combination of RotatE and box embeddings.
