27 citations · 109 across the 23 of their papers we have counts for
25 papers
DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck
Shubham Agarwal, Akshat Gupta, Mike Heddes +21
Evaluation has been central to advances in AI, and it is equally critical to autonomous discovery. Yet scaling autonomous discovery to real-world engineering challenges faces a fun…
Weight Tying Biases Token Embeddings Towards the Output Space
Antonio Lopardo, Avyukth Harish, Catherine Arnett +1
Weight tying, i.e. sharing parameters between input and output embedding matrices, is common practice in language model design, yet its impact on the learned embedding space remain…
PokerBench: Training Large Language Models to become Professional Poker Players
Richard Zhuang, Akshat Gupta, Richard Yang +3
We introduce PokerBench - a benchmark for evaluating the poker-playing abilities of large language models (LLMs). As LLMs excel in traditional NLP tasks, their application to compl…
Sylber: Syllabic Embedding Representation of Speech from Raw Audio
Cheol Jun Cho, Nicholas Lee, Akshat Gupta +4
Syllables are compositional units of spoken language that efficiently structure human speech perception and production. However, current neural speech representations lack such str…
FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression
Fazal Mittu, Yihuan Bu, Akshat Gupta +4
While the language modeling objective has been shown to be deeply connected with compression, it is surprising that modern LLMs are not employed in practical text compression syste…
Geometric Interpretation of Layer Normalization and a Comparative Analysis with RMSNorm
Akshat Gupta, Atahan Ozdemir, Gopala Anumanchipalli
This paper presents a novel geometric interpretation of LayerNorm and explores how LayerNorm influences the norm and orientation of hidden vectors in the representation space. With…
Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3
Junsang Yoon, Akshat Gupta, Gopala Anumanchipalli
This study presents a targeted model editing analysis focused on the latest large language model, Llama-3. We explore the efficacy of popular model editing techniques - ROME, MEMIT…
A Unified Framework for Model Editing
Akshat Gupta, Dev Sajnani, Gopala Anumanchipalli
ROME and MEMIT are largely believed to be two different model editing algorithms, with the major difference between them being the ability to perform batched edits. In this paper,…
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
Akshat Gupta, Sidharth Baskaran, Gopala Anumanchipalli
Recent work using Rank-One Model Editing (ROME), a popular model editing method, has shown that there are certain facts that the algorithm is unable to edit without breaking the mo…
Identifying Multiple Personalities in Large Language Models with External Evaluation
Xiaoyang Song, Yuta Adachi, Jessie Feng +6
As Large Language Models (LLMs) are integrated with human daily applications rapidly, many societal and ethical concerns are raised regarding the behavior of LLMs. One of the ways…
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
Akshat Gupta, Anurag Rao, Gopala Anumanchipalli
Editing knowledge in large language models is an attractive capability to have which allows us to correct incorrectly learnt facts during pre-training, as well as update the model…
Self-Assessment Tests are Unreliable Measures of LLM Personality
Akshat Gupta, Xiaoyang Song, Gopala Anumanchipalli
As large language models (LLM) evolve in their capabilities, various recent studies have tried to quantify their behavior using psychological tools created to study human behavior.…
Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis
Akshat Gupta
Since the introduction of ChatGPT and GPT-4, these models have been tested across a large number of tasks. Their adeptness across domains is evident, but their aptitude in playing…
Probing Quantifier Comprehension in Large Language Models: Another Example of Inverse Scaling
Akshat Gupta
With their increasing size, large language models (LLMs) are becoming increasingly good at language understanding tasks. But even with high performance on specific downstream task,…
Have Large Language Models Developed a Personality?: Applicability of Self-Assessment Tests in Measuring Personality in LLMs
Xiaoyang Song, Akshat Gupta, Kiyan Mohebbizadeh +2
Have Large Language Models (LLMs) developed a personality? The short answer is a resounding "We Don't Know!". In this paper, we show that we do not yet have the right tools to meas…
REFinD: Relation Extraction Financial Dataset
Simerjot Kaur, Charese Smiley, Akshat Gupta +5
A number of datasets for Relation Extraction (RE) have been created to aide downstream tasks such as information retrieval, semantic search, question answering and textual entailme…
On Building Spoken Language Understanding Systems for Low Resourced Languages
Akshat Gupta
Spoken dialog systems are slowly becoming and integral part of the human experience due to their various advantages over textual interfaces. Spoken language understanding (SLU) sys…
Intent Recognition and Unsupervised Slot Identification for Low Resourced Spoken Dialog Systems
Akshat Gupta, Olivia Deng, Akruti Kushwaha +4
Intent Recognition and Slot Identification are crucial components in spoken language understanding (SLU) systems. In this paper, we present a novel approach towards both these task…
SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification
Sai Muralidhar Jayanthi, Akshat Gupta
In this paper we present our submission for the EACL 2021-Shared Task on Offensive Language Identification in Dravidian languages. Our final system is an ensemble of mBERT and XLM-…
Unsupervised Self-Training for Sentiment Analysis of Code-Switched Data
Akshat Gupta, Sargam Menghani, Sai Krishna Rallabandi +1
Sentiment analysis is an important task in understanding social media content like customer reviews, Twitter and Facebook feeds etc. In multilingual communities around the world, a…
Task-Specific Pre-Training and Cross Lingual Transfer for Code-Switched Data
Akshat Gupta, Sai Krishna Rallabandi, Alan Black
Using task-specific pre-training and leveraging cross-lingual transfer are two of the most popular ways to handle code-switched data. In this paper, we aim to compare the effects o…
Acoustics Based Intent Recognition Using Discovered Phonetic Units for Low Resource Languages
Akshat Gupta, Xinjian Li, Sai Krishna Rallabandi +1
With recent advancements in language technologies, humans are now speaking to devices. Increasing the reach of spoken language technologies requires building systems in local langu…
Mere account mein kitna balance hai? -- On building voice enabled Banking Services for Multilingual Communities
Akshat Gupta, Sai Krishna Rallabandi, Alan W Black
Tremendous progress in speech and language processing has brought language technologies closer to daily human life. Voice technology has the potential to act as a horizontal enabli…
Stochastic Lagrangian Dynamics of Vorticity. II. Channel-Flow Turbulence
Gregory L. Eyink, Akshat Gupta, Tamer Zaki
We here exploit a rigorous mathematical theory of vorticity dynamics for Navier-Stokes solutions in terms of stochastic Lagrangian flows and their stochastic Cauchy invariants, tha…