Search Results for author: Sarkar Snigdha Sarathi Das

Found 13 papers, 9 papers with code

GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers

1 code implementation12 Dec 2024 Sarkar Snigdha Sarathi Das, Ryo Kamoi, Bo Pang, Yusen Zhang, Caiming Xiong, Rui Zhang

The effectiveness of large language models (LLMs) is closely tied to the design of prompts, making prompt optimization essential for enhancing their performance across a wide range of tasks.

GSM8K Prompt Engineering

VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information

1 code implementation1 Dec 2024 Ryo Kamoi, Yusen Zhang, Sarkar Snigdha Sarathi Das, Ranran Haoran Zhang, Rui Zhang

In this work, we introduce VisOnlyQA, a new dataset designed to directly evaluate the visual perception capabilities of LVLMs on questions about geometric and numerical information in scientific figures.

Multiple-choice

Verbosity $\neq$ Veracity: Demystify Verbosity Compensation Behavior of Large Language Models

1 code implementation12 Nov 2024 Yusen Zhang, Sarkar Snigdha Sarathi Das, Rui Zhang

Both 1) and 2) highlight the urgent need to mitigate the frequency of VC behavior and disentangle verbosity with veracity.

Hallucination

Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning

1 code implementation7 Nov 2023 Sarkar Snigdha Sarathi Das, Ranran Haoran Zhang, Peng Shi, Wenpeng Yin, Rui Zhang

Unfortunately, this requires formatting them into specialized augmented format unknown to the base pretrained language model (PLMs) necessitating finetuning to the target format.

In-Context Learning Language Modeling +8

Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies

no code implementations14 Sep 2023 Chirag Shah, Ryen W. White, Reid Andersen, Georg Buscher, Scott Counts, Sarkar Snigdha Sarathi Das, Ali Montazer, Sathish Manivannan, Jennifer Neville, Xiaochuan Ni, Nagu Rangan, Tara Safavi, Siddharth Suri, Mengting Wan, Leijie Wang, Longqi Yang

However, using LLMs to generate a user intent taxonomy and apply it for log analysis can be problematic for two main reasons: (1) such a taxonomy is not externally validated; and (2) there may be an undesirable feedback loop.

A Survey on Deep Learning Based Point-Of-Interest (POI) Recommendations

no code implementations20 Nov 2020 Md. Ashraful Islam, Mir Mahathir Mohammad, Sarkar Snigdha Sarathi Das, Mohammed Eunus Ali

Our work categorizes and critically analyzes the recent POI recommendation works based on different deep learning paradigms and other relevant features.

Deep Learning Recommendation Systems

Boosting House Price Predictions using Geo-Spatial Network Embedding

1 code implementation1 Sep 2020 Sarkar Snigdha Sarathi Das, Mohammed Eunus Ali, Yuan-Fang Li, Yong-Bin Kang, Timos Sellis

Extensive experiments with a large number of regression techniques show that the embeddings produced by our proposed GSNE technique consistently and significantly improve the performance of the house price prediction task regardless of the downstream regression model.

Network Embedding Prediction +1

CCCNet: An Attention Based Deep Learning Framework for Categorized Crowd Counting

no code implementations12 Dec 2019 Sarkar Snigdha Sarathi Das, Syed Md. Mukit Rashid, Mohammed Eunus Ali

In this paper, we introduce a new variant of crowd counting problem, namely "Categorized Crowd Counting", that counts the number of people sitting and standing in a given image.

Crowd Counting Management

Cannot find the paper you are looking for? You can Submit a new open access paper.