AI support of collaborative interactions entails mediating potential misalignment between interlocutor beliefs.Common preference alignment methods like DPO excel in static settings, but struggle in dynamic collaborative tasks where the explicit signals of interlocutor beliefs are sparse and skewed.We propose the Frictional Agent Alignment Framework (FAAF), to generate precise, context-aware "friction" that prompts for deliberation and re-examination of existing evidence.FAAF's two-player objective decouples from data skew: a frictive-state policy identifies belief misalignments, while an intervention policy crafts collaborator-preferred responses.We derive an analytical solution to this objective, enabling training a single policy via a simple supervised loss.Experiments on three benchmarks show FAAF outperforms competitors in producing concise, interpretable friction and in OOD generalization.By aligning LLMs to act as adaptive "thought partners"-not passive responders-FAAF advances scalable, dynamic human-AI collaboration.Our code and data can be found at https: //github.com/csu-signal/FAAF_ACL.

Abhijnan Nath, Andrey Volozin, Saumajit Saha, Albert Aristotle Nanda, Galina Grunin, Rahul Bhotika, Nikhil Krishnaswamy. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

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 evaluate their abilities to collaborate effectively in multi-turn, multi-party tasks. In this paper, we build on the AI alignment and “safe interruptability” literature to offer novel theoretical insights on collaborative behavior between LLM-driven *collaborator agents* and an *intervention agent*. Our goal is to learn an ideal “partner-aware” collaborator that increases the group’s common-ground (CG)—alignment on task-relevant propositions—by intelligently collecting information provided in *interventions* by a partner agent. We show how LLM agents trained using standard RLHF and related approaches are naturally inclined to ignore possibly well-meaning interventions, which makes increasing group common ground non-trivial in this setting. We employ a two-player Modified-Action MDP to examine this suboptimal behavior of standard AI agents, and propose **Interruptible Collaborative Roleplayer (ICR)**—a novel “partner-aware” learning algorithm to train CG-optimal collaborators. Experiments on multiple collaborative task environments show that ICR, on average, is more capable of promoting successful CG convergence and exploring more diverse solutions in such tasks.

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 occurrence. Images of the events can help facilitate resolution when language is ambiguous. Here, we propose a multimodal cross-document event coreference resolution method that integrates visual and textual cues with a simple linear map between vision and language models. As existing ECR benchmark datasets rarely provide images for all event mentions, we augment the popular ECB+ dataset with event-centric images scraped from the internet and generated using image diffusion models. We establish three methods that incorporate images and text for coreference: 1) a standard fused model with finetuning, 2) a novel linear mapping method without finetuning and 3) an ensembling approach based on splitting mention pairs by semantic and discourse-level difficulty. We evaluate on 2 datasets: the augmented ECB+, and AIDA Phase 1. Our ensemble systems using cross-modal linear mapping establish an upper limit (91.9 CoNLL F1) on ECB+ ECR performance given the preprocessing assumptions used, and establish a novel baseline on AIDA Phase 1. Our results demonstrate the utility of multimodal information in ECR for certain challenging coreference problems, and highlight a need for more multimodal resources in the coreference resolution space.

Abhijnan Nath, Shadi Manafi Avari, Avyakta Chelle, Nikhil Krishnaswamy. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Loanwords are words incorporated from one language into another without translation. Suppose two words from distantly-related or unrelated languages sound similar and have a similar meaning. In that case, this is evidence of likely borrowing. This paper presents a method to automatically detect loanwords across various language pairs, accounting for differences in script, pronunciation and phonetic transformation by the borrowing language. We incorporate edit distance, semantic similarity measures, and phonetic alignment. We evaluate on 12 language pairs and achieve performance comparable to or exceeding state of the art methods on single-pair loanword detection tasks. We also demonstrate that multilingual models perform the same or often better than models trained on single language pairs and can potentially generalize to unseen language pairs with sufficient data, and that our method can exceed human performance on loanword detection.