8 citations · 31 across the 12 of their papers we have counts for
13 papers
Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants
Jiazhou Liang, Liam Gallagher, Kiko Chen +4
Egocentric assistants must connect what users say with what they see across long interaction histories. We formalize this challenge as Spatially grounded Conversational Reasoning (…
Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems
Jiazhou Liang, Armin Toroghi, Yifan Simon Liu +3
LLM-based conversational AI agents struggle to maintain coherent behavior over long horizons due to limited context. While RAG-based approaches are increasingly adopted to overcome…
Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents
Yifan Simon Liu, Liam Gallagher, Faeze Moradi Kalarde +3
Long-horizon conversational agents need to interact with users through evolving events, tasks, and goals. Such histories are naturally temporal, yet many existing memory systems or…
CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models
Armin Toroghi, Faeze Moradi Kalarde, Scott Sanner
To effectively interact with the real world, Large Language Models (LLMs) require entity-based commonsense reasoning, a challenging task that necessitates integrating factual knowl…
Semantic XPath: Structured Agentic Memory Access for Conversational AI
Yifan Simon Liu, Ruifan Wu, Liam Gallagher +3
Conversational AI (ConvAI) agents increasingly maintain structured memory to support long-term, task-oriented interactions. In-context memory approaches append the growing history…
Multimodal Item Scoring for Natural Language Recommendation via Gaussian Process Regression with LLM Relevance Judgments
Yifan Liu, Qianfeng Wen, Jiazhou Liang +6
Natural Language Recommendation (NLRec) generates item suggestions based on the relevance between user-issued NL requests and NL item description passages. Existing NLRec approache…
CoLoTa: A Dataset for Entity-based Commonsense Reasoning over Long-Tail Knowledge
Armin Toroghi, Willis Guo, Scott Sanner
The rise of Large Language Models (LLMs) has redefined the AI landscape, particularly due to their ability to encode factual and commonsense knowledge, and their outstanding perfor…
Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation
David Eric Austin, Anton Korikov, Armin Toroghi +1
Designing preference elicitation (PE) methodologies that can quickly ascertain a user's top item preferences in a cold-start setting is a key challenge for building effective and p…
CR-LT-KGQA: A Knowledge Graph Question Answering Dataset Requiring Commonsense Reasoning and Long-Tail Knowledge
Willis Guo, Armin Toroghi, Scott Sanner
Knowledge graph question answering (KGQA) is a well-established field that seeks to provide factual answers to natural language (NL) questions by leveraging knowledge graphs (KGs).…
Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering
Armin Toroghi, Willis Guo, Mohammad Mahdi Abdollah Pour +1
Knowledge Graph Question Answering (KGQA) methods seek to answer Natural Language questions using the relational information stored in Knowledge Graphs (KGs). With the recent advan…
Self-Supervised Contrastive BERT Fine-tuning for Fusion-based Reviewed-Item Retrieval
Mohammad Mahdi Abdollah Pour, Parsa Farinneya, Armin Toroghi +6
As natural language interfaces enable users to express increasingly complex natural language queries, there is a parallel explosion of user review content that can allow users to b…
Bayesian Knowledge-driven Critiquing with Indirect Evidence
Armin Toroghi, Griffin Floto, Zhenwei Tang +1
Conversational recommender systems (CRS) enhance the expressivity and personalization of recommendations through multiple turns of user-system interaction. Critiquing is a well-kno…
LogicRec: Recommendation with Users' Logical Requirements
Zhenwei Tang, Griffin Floto, Armin Toroghi +3
Users may demand recommendations with highly personalized requirements involving logical operations, e.g., the intersection of two requirements, where such requirements naturally f…