1 citations · 1 across the 12 of their papers we have counts for
14 papers
PocketTSLM: Deploying an On-Device Soft-Prompt Time-Series Language Model for Privacy-Preserving Smartphone Reasoning
Max Rosenblattl, Nikhil Krishnaswamy, Leon Nissen +9
Consumer phones and wearables increasingly collect physiological time-series data, yet most mobile systems treat these streams as summaries or text rather than as temporal evidence…
Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry
Hannah VanderHoeven, Abhijnan Nath, Nikhil Krishnaswamy
Fruitful collaborations require effective communication of privately-held information. The increasing use of LLMs as "collaborators" raises questions about the extent to which they…
ECHO: Learning Epistemically Adaptive Language Agents with Turn-Level Credit
Abhijnan Nath, Nikhil Krishnaswamy, Sifatul Anindho
Effective multi-turn agents must decide what information to seek, how to use new evidence, and when they are certain enough to act. We introduce Epistemic Decision Processes (EDPs)…
CRAFT: Grounded Multi-Agent Coordination Under Partial Information
Abhijnan Nath, Hannah VanderHoeven, Nikhil Krishnaswamy
We introduce CRAFT, a multi-agent benchmark for evaluating pragmatic communication in large language models under strict partial information. In this setting, multiple agents with…
Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs
Abhijnan Nath, Alireza Bagheri Garakani, Tianchen Zhou +3
Large language models are increasingly trained via reinforcement learning for personalized recommendation tasks, but standard methods like GRPO rely on sparse, sequence-level rewar…
Learning "Partner-Aware" Collaborators in Multi-Party Collaboration
Abhijnan Nath, Nikhil Krishnaswamy
Large Language Models (LLMs) are increasingly being deployed in agentic settings where they act as collaborators with humans. Therefore, it is increasingly important to be able to…
Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes
Abhijnan Nath, Carine Graff, Nikhil Krishnaswamy
As Large Language Models (LLMs) get integrated into diverse workflows, they are increasingly being regarded as "collaborators" with humans, and required to work in coordination wit…
Dynamic Epistemic Friction in Dialogue
Timothy Obiso, Kenneth Lai, Abhijnan Nath +2
Recent developments in aligning Large Language Models (LLMs) with human preferences have significantly enhanced their utility in human-AI collaborative scenarios. However, such app…
Frictional Agent Alignment Framework: Slow Down and Don't Break Things
Abhijnan Nath, Carine Graff, Andrei Bachinin +1
AI support of collaborative interactions entails mediating potential misalignment between interlocutor beliefs. Common preference alignment methods like DPO excel in static setting…
Any Other Thoughts, Hedgehog? Linking Deliberation Chains in Collaborative Dialogues
Abhijnan Nath, Videep Venkatesha, Mariah Bradford +5
Question-asking in collaborative dialogue has long been established as key to knowledge construction, both in internal and collaborative problem solving. In this work, we examine p…
Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both
Abhijnan Nath, Changsoo Jung, Ethan Seefried +1
Traditional RLHF-based LLM alignment methods explicitly maximize the expected rewards from a separate reward model. More recent supervised alignment methods like Direct Preference…
Multimodal Cross-Document Event Coreference Resolution Using Linear Semantic Transfer and Mixed-Modality Ensembles
Abhijnan Nath, Huma Jamil, Shafiuddin Rehan Ahmed +5
Event coreference resolution (ECR) is the task of determining whether distinct mentions of events within a multi-document corpus are actually linked to the same underlying occurren…
Okay, Let's Do This! Modeling Event Coreference with Generated Rationales and Knowledge Distillation
Abhijnan Nath, Shadi Manafi, Avyakta Chelle +1
In NLP, Event Coreference Resolution (ECR) is the task of connecting event clusters that refer to the same underlying real-life event, usually via neural systems. In this work, we…
Cross-Lingual Transfer Robustness to Lower-Resource Languages on Adversarial Datasets
Shadi Manafi, Nikhil Krishnaswamy
Multilingual Language Models (MLLMs) exhibit robust cross-lingual transfer capabilities, or the ability to leverage information acquired in a source language and apply it to a targ…