1.2k citations · 1.7k across the 23 of their papers we have counts for
24 papers
ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders
Ofer Meshi, Krisztian Balog, Sally Goldman +5
The promise of LLM-based user simulators to improve conversational AI is hindered by a critical "realism gap," leading to systems that are optimized for simulated interactions, but…
RouteNator: A Router-Based Multi-Modal Architecture for Generating Synthetic Training Data for Function Calling LLMs
Vibha Belavadi, Tushar Vatsa, Dewang Sultania +5
This paper addresses fine-tuning Large Language Models (LLMs) for function calling tasks when real user interaction data is unavailable. In digital content creation tools, where us…
Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai
Parinthapat Pengpun, Can Udomcharoenchaikit, Weerayut Buaphet +1
We present a synthetic data approach for instruction-tuning large language models (LLMs) for low-resource languages in a data-efficient manner, specifically focusing on Thai. We id…
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Gemini Team, Petko Georgiev, Ving Ian Lei +1132
In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over…
Assessing biomedical knowledge robustness in large language models by query-efficient sampling attacks
R. Patrick Xian, Alex J. Lee, Satvik Lolla +4
The increasing depth of parametric domain knowledge in large language models (LLMs) is fueling their rapid deployment in real-world applications. Understanding model vulnerabilitie…
Instruction-Following Evaluation for Large Language Models
Jeffrey Zhou, Tianjian Lu, Swaroop Mishra +5
One core capability of Large Language Models (LLMs) is to follow natural language instructions. However, the evaluation of such abilities is not standardized: Human evaluations are…
PaLM 2 Technical Report
Rohan Anil, Andrew M. Dai, Orhan Firat +125
We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 i…
Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference
Tao Lei, Junwen Bai, Siddhartha Brahma +9
We propose Conditional Adapter (CoDA), a parameter-efficient transfer learning method that also improves inference efficiency. CoDA generalizes beyond standard adapter approaches t…
CoLT5: Faster Long-Range Transformers with Conditional Computation
Joshua Ainslie, Tao Lei, Michiel de Jong +9
Many natural language processing tasks benefit from long inputs, but processing long documents with Transformers is expensive -- not only due to quadratic attention complexity but…
Multi-Vector Retrieval as Sparse Alignment
Yujie Qian, Jinhyuk Lee, Sai Meher Karthik Duddu +5
Multi-vector retrieval models improve over single-vector dual encoders on many information retrieval tasks. In this paper, we cast the multi-vector retrieval problem as sparse alig…
Breaking BERT: Evaluating and Optimizing Sparsified Attention
Siddhartha Brahma, Polina Zablotskaia, David Mimno
Transformers allow attention between all pairs of tokens, but there is reason to believe that most of these connections - and their quadratic time and memory - may not be necessary…
Scaling Instruction-Finetuned Language Models
Hyung Won Chung, Le Hou, Shayne Longpre +32
Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we expl…
Improved Semantic Role Labeling using Parameterized Neighborhood Memory Adaptation
Ishan Jindal, Ranit Aharonov, Siddhartha Brahma +2
Deep neural models achieve some of the best results for semantic role labeling. Inspired by instance-based learning that utilizes nearest neighbors to handle low-frequency context-…
CLAR: A Cross-Lingual Argument Regularizer for Semantic Role Labeling
Ishan Jindal, Yunyao Li, Siddhartha Brahma +1
Semantic role labeling (SRL) identifies predicate-argument structure(s) in a given sentence. Although different languages have different argument annotations, polyglot training, th…
Small but Mighty: New Benchmarks for Split and Rephrase
Li Zhang, Huaiyu Zhu, Siddhartha Brahma +1
Split and Rephrase is a text simplification task of rewriting a complex sentence into simpler ones. As a relatively new task, it is paramount to ensure the soundness of its evaluat…
On Pliable Index Coding
Shanuja Sasi, B. Sundar Rajan
A new variant of index coding problem termed as Pliable Index Coding Problem (PICOD) is formulated in [S. Brahma, C. Fragouli, "Pliable index coding", IEEE Transactions on Informat…
REGMAPR - Text Matching Made Easy
Siddhartha Brahma
Text matching is a fundamental problem in natural language processing. Neural models using bidirectional LSTMs for sentence encoding and inter-sentence attention mechanisms perform…
Efficiently Processing Workflow Provenance Queries on SPARK
Rajmohan C, Pranay Lohia, Himanshu Gupta +3
In this paper, we investigate how we can leverage Spark platform for efficiently processing provenance queries on large volumes of workflow provenance data. We focus on processing…
Improved Language Modeling by Decoding the Past
Siddhartha Brahma
Highly regularized LSTMs achieve impressive results on several benchmark datasets in language modeling. We propose a new regularization method based on decoding the last token in t…
Unsupervised Learning of Sentence Representations Using Sequence Consistency
Siddhartha Brahma
Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose ConsSent, a simple yet surprisingly powerful unsupervi…
Improved Sentence Modeling using Suffix Bidirectional LSTM
Siddhartha Brahma
Recurrent neural networks have become ubiquitous in computing representations of sequential data, especially textual data in natural language processing. In particular, Bidirection…
On the scaling of polynomial features for representation matching
Siddhartha Brahma
In many neural models, new features as polynomial functions of existing ones are used to augment representations. Using the natural language inference task as an example, we invest…
SufiSent - Universal Sentence Representations Using Suffix Encodings
Siddhartha Brahma
Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose a method to learn such representations by encoding the…
Consistency in the face of change: an adaptive approach to physical layer cooperation
Ayan Sengupta, Yahya H. Ezzeldin, Siddhartha Brahma +2
Most existing works on physical-layer (PHY) cooperation (beyond routing) focus on how to best use a given, static relay network--while wireless networks are anything but static. In…