468 citations · 558 across the 22 of their papers we have counts for
23 papers
A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation
Bohan Yao, Vikas Yadav
Augmenting large language models (LLMs) with external tools is a promising avenue for developing high-performance mathematical reasoning systems. Prior tool-augmented approaches ty…
Apriel-Nemotron-15B-Thinker
Shruthan Radhakrishna, Soham Parikh, Gopal Sarda +32
While large language models (LLMs) have achieved remarkable reasoning capabilities across domains like code, math and other enterprise tasks, their significant memory and computati…
BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
Ahmed Masry, Abhay Puri, Masoud Hashemi +13
Charts are essential to data analysis, transforming raw data into clear visual representations that support human decision-making. Although current vision-language models (VLMs) ha…
ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models
Razvan-Gabriel Dumitru, Darius Peteleaza, Vikas Yadav +1
Large language models excel at complex tasks by breaking down problems into structured reasoning steps. However, reasoning traces often extend beyond reaching a correct answer, cau…
Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models
Meghana Rajeev, Rajkumar Ramamurthy, Prapti Trivedi +5
We investigate the robustness of reasoning models trained for step-by-step problem solving by introducing query-agnostic adversarial triggers - short, irrelevant text that, when ap…
CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality
Razvan-Gabriel Dumitru, Minglai Yang, Vikas Yadav +1
We introduce CopySpec, a simple yet effective technique to tackle the inefficiencies LLMs face when generating responses that closely resemble previous outputs or responses that ca…
Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework
Aman Tiwari, Shiva Krishna Reddy Malay, Vikas Yadav +2
Graph databases like Neo4j are gaining popularity for handling complex, interconnected data, over traditional relational databases in modeling and querying relationships. While tra…
Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy
Razvan-Gabriel Dumitru, Paul-Ioan Clotan, Vikas Yadav +2
This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established b…
Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models
Nishanth Madhusudhan, Sathwik Tejaswi Madhusudhan, Vikas Yadav +1
Abstention Ability (AA) is a critical aspect of Large Language Model (LLM) reliability, referring to an LLM's capability to withhold responses when uncertain or lacking a definitiv…
Explicit Diversity Conditions for Effective Question Answer Generation with Large Language Models
Vikas Yadav, Hyuk Joon Kwon, Vijay Srinivasan +1
Question Answer Generation (QAG) is an effective data augmentation technique to improve the accuracy of question answering systems, especially in low-resource domains. While recent…
Paraphrase and Aggregate with Large Language Models for Minimizing Intent Classification Errors
Vikas Yadav, Zheng Tang, Vijay Srinivasan
Large language models (LLM) have achieved remarkable success in natural language generation but lesser focus has been given to their applicability in decision making tasks such as…
Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels
Razvan-Gabriel Dumitru, Vikas Yadav, Rishabh Maheshwary +3
We present a simple meta quantization approach that quantizes different layers of a large language model (LLM) at different bit levels, and is independent of the underlying quantiz…
M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models
Rishabh Maheshwary, Vikas Yadav, Hoang Nguyen +2
Instruction finetuning (IFT) is critical for aligning Large Language Models (LLMs) to follow instructions. While many effective IFT datasets have been introduced recently, they pre…
Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferences
Pulkit Pattnaik, Rishabh Maheshwary, Kelechi Ogueji +2
Direct Preference Optimization (DPO) is an effective technique that leverages pairwise preference data (usually one chosen and rejected response pair per user prompt) to align LLMs…
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
Jun Yan, Vikas Yadav, Shiyang Li +6
Instruction-tuned Large Language Models (LLMs) have become a ubiquitous platform for open-ended applications due to their ability to modulate responses based on human instructions.…
AlpaGasus: Training A Better Alpaca with Fewer Data
Lichang Chen, Shiyang Li, Jun Yan +8
Large language models (LLMs) strengthen instruction-following capability through instruction-finetuning (IFT) on supervised instruction/response data. However, widely used IFT data…
Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading
Hoang Van, Vikas Yadav, Mihai Surdeanu
We propose a simple and effective strategy for data augmentation for low-resource machine reading comprehension (MRC). Our approach first pretrains the answer extraction components…
Towards Robust Neural Retrieval Models with Synthetic Pre-Training
Revanth Gangi Reddy, Vikas Yadav, Md Arafat Sultan +4
Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems. However,…
Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering
Vikas Yadav, Steven Bethard, Mihai Surdeanu
Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method. We i…
Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering
Vikas Yadav, Steven Bethard, Mihai Surdeanu
We propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) that (a) maximizes the relevance of the selected sentences, (…
A Survey on Recent Advances in Named Entity Recognition from Deep Learning models
Vikas Yadav, Steven Bethard
Named Entity Recognition (NER) is a key component in NLP systems for question answering, information retrieval, relation extraction, etc. NER systems have been studied and develope…
Multi-class Hierarchical Question Classification for Multiple Choice Science Exams
Dongfang Xu, Peter Jansen, Jaycie Martin +5
Prior work has demonstrated that question classification (QC), recognizing the problem domain of a question, can help answer it more accurately. However, developing strong QC algor…
Sanity Check: A Strong Alignment and Information Retrieval Baseline for Question Answering
Vikas Yadav, Rebecca Sharp, Mihai Surdeanu
While increasingly complex approaches to question answering (QA) have been proposed, the true gain of these systems, particularly with respect to their expensive training requireme…