activity
20162026
most citedBERT & Family Eat Word Salad: Experiments with Text Understanding

24 citations · 36 across the 29 of their papers we have counts for

collaborators
Showing 2024Show all

6 papers · 1 filter

cs.CL2024

Understanding the Logic of Direct Preference Alignment through Logic

Kyle Richardson, Vivek Srikumar, Ashish Sabharwal

Recent direct preference alignment algorithms (DPA), such as DPO, have shown great promise in aligning large language models to human preferences. While this has motivated the deve…

cs.CL2024

State Space Models are Strong Text Rerankers

Zhichao Xu, Jinghua Yan, Ashim Gupta +1

Transformers dominate NLP and IR; but their inference inefficiencies and challenges in extrapolating to longer contexts have sparked interest in alternative model architectures. Am…

cs.CL2024

Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression

Zhichao Xu, Ashim Gupta, Tao Li +2

Increasingly, model compression techniques enable large language models (LLMs) to be deployed in real-world applications. As a result of this momentum towards local deployment, com…

cs.CL2024

An Empirical Investigation of Matrix Factorization Methods for Pre-trained Transformers

Ashim Gupta, Sina Mahdipour Saravani, P. Sadayappan +1

The increasing size of transformer-based models in NLP makes the question of compressing them important. In this work, we present a comprehensive analysis of factorization based mo…

cs.CL20241 cited

In-Context Example Ordering Guided by Label Distributions

Zhichao Xu, Daniel Cohen, Bei Wang +1

By allowing models to predict without task-specific training, in-context learning (ICL) with pretrained LLMs has enormous potential in NLP. However, a number of problems persist in…

cs.CL2024

Promptly Predicting Structures: The Return of Inference

Maitrey Mehta, Valentina Pyatkin, Vivek Srikumar

Prompt-based methods have been used extensively across NLP to build zero- and few-shot label predictors. Many NLP tasks are naturally structured: that is, their outputs consist of…