6 citations · 8 across the 10 of their papers we have counts for
12 papers
Understanding LLM Parameter Update Sparsity through the Lens of Fisher
Yufan Zhang, Sagnik Mukherjee, Hao Peng
Recent studies have observed that parameter changes during language-model post-training can be concentrated in a small subset of coordinates. This phenomenon has been reported in r…
ISO: An RLVR-Native Optimization Stack
Hanqing Zhu, Wenyan Cong, Zhizhou Sha +8
Reinforcement learning with verifiable rewards (RLVR) advances the reasoning capabilities of language models, yet the optimization layer that converts reward feedback into weight-s…
Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
Sagnik Mukherjee, Lifan Yuan, Pavan Jayasinha +2
Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs) and a key focus of current scaling e…
Graph Neural Network Assisted Genetic Algorithm for Structural Dynamic Response and Parameter Optimization
Sagnik Mukherjee, Indrajit Barua
The optimization of structural parameters, such as mass(m), stiffness(k), and damping coefficient(c), is critical for designing efficient, resilient, and stable structures. Convent…
ReasoningFlow: Semantic Structure of Complex Reasoning Traces
Jinu Lee, Sagnik Mukherjee, Dilek Hakkani-Tur +1
Large reasoning models (LRMs) generate complex reasoning traces with planning, reflection, verification, and backtracking. In this work, we introduce ReasoningFlow, a unified schem…
Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
Sagnik Mukherjee, Lifan Yuan, Dilek Hakkani-Tur +1
Reinforcement learning (RL) yields substantial improvements in large language models (LLMs) downstream task performance and alignment with human values. Surprisingly, such large ga…
Infogent: An Agent-Based Framework for Web Information Aggregation
Revanth Gangi Reddy, Sagnik Mukherjee, Jeonghwan Kim +3
Despite seemingly performant web agents on the task-completion benchmarks, most existing methods evaluate the agents based on a presupposition: the web navigation task consists of…
Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting
Sagnik Mukherjee, Muhammad Farid Adilazuarda, Sunayana Sitaram +3
Socio-demographic prompting is a commonly employed approach to study cultural biases in LLMs as well as for aligning models to certain cultures. In this paper, we systematically pr…
Towards Measuring and Modeling "Culture" in LLMs: A Survey
Muhammad Farid Adilazuarda, Sagnik Mukherjee, Pradhyumna Lavania +5
We present a survey of more than 90 recent papers that aim to study cultural representation and inclusion in large language models (LLMs). We observe that none of the studies expli…
On the Robustness of Reading Comprehension Models to Entity Renaming
Jun Yan, Yang Xiao, Sagnik Mukherjee +3
We study the robustness of machine reading comprehension (MRC) models to entity renaming -- do models make more wrong predictions when the same questions are asked about an entity…
WASSA@IITK at WASSA 2021: Multi-task Learning and Transformer Finetuning for Emotion Classification and Empathy Prediction
Jay Mundra, Rohan Gupta, Sagnik Mukherjee
This paper describes our contribution to the WASSA 2021 shared task on Empathy Prediction and Emotion Classification. The broad goal of this task was to model an empathy score, a d…
IITK@LCP at SemEval 2021 Task 1: Classification for Lexical Complexity Regression Task
Neil Rajiv Shirude, Sagnik Mukherjee, Tushar Shandhilya +2
This paper describes our contribution to SemEval 2021 Task 1: Lexical Complexity Prediction. In our approach, we leverage the ELECTRA model and attempt to mirror the data annotatio…