52 citations · 62 across the 22 of their papers we have counts for
28 papers
TeleTune: Evolving Agent Skills From Offline Telemetry
Justin Chih-Yao Chen, Elias Stengel-Eskin, Yan Chen +6
Computer-use agents need to capture procedural knowledge of how people use software. User telemetry offers a scalable source of this knowledge. However, learning reusable skills fr…
Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting
Michael Y. Hu, Benjamin Van Durme, Jacob Andreas +1
Language model (LM) agents deployed in novel environments often exhibit poor sample efficiency when learning from sequential interactions. This significantly hinders the usefulness…
LM Agents for Coordinating Multi-User Information Gathering
Harsh Jhamtani, Jacob Andreas, Benjamin Van Durme
This paper introduces PeopleJoin, a benchmark for evaluating LM-mediated collaborative problem solving. Given a user request, PeopleJoin agents must identify teammates who might be…
Towards Robust Evaluation of Unlearning in LLMs via Data Transformations
Abhinav Joshi, Shaswati Saha, Divyaksh Shukla +4
Large Language Models (LLMs) have shown to be a great success in a wide range of applications ranging from regular NLP-based use cases to AI agents. LLMs have been trained on a vas…
Steering Large Language Models between Code Execution and Textual Reasoning
Yongchao Chen, Harsh Jhamtani, Srinagesh Sharma +2
While a lot of recent research focuses on enhancing the textual reasoning capabilities of Large Language Models (LLMs) by optimizing the multi-agent framework or reasoning chains,…
Learning to Retrieve Iteratively for In-Context Learning
Yunmo Chen, Tongfei Chen, Harsh Jhamtani +4
We introduce iterative retrieval, a novel framework that empowers retrievers to make iterative decisions through policy optimization. Finding an optimal portfolio of retrieved item…
Interpreting User Requests in the Context of Natural Language Standing Instructions
Nikita Moghe, Patrick Xia, Jacob Andreas +3
Users of natural language interfaces, generally powered by Large Language Models (LLMs),often must repeat their preferences each time they make a similar request. We describe an ap…
SCREWS: A Modular Framework for Reasoning with Revisions
Kumar Shridhar, Harsh Jhamtani, Hao Fang +3
Large language models (LLMs) can improve their accuracy on various tasks through iteratively refining and revising their output based on feedback. We observe that these revisions c…
Natural Language Decomposition and Interpretation of Complex Utterances
Harsh Jhamtani, Hao Fang, Patrick Xia +3
Designing natural language interfaces has historically required collecting supervised data to translate user requests into carefully designed intent representations. This requires…
Ontologically Faithful Generation of Non-Player Character Dialogues
Nathaniel Weir, Ryan Thomas, Randolph D'Amore +3
We introduce a language generation task grounded in a popular video game environment. KNUDGE (KNowledge Constrained User-NPC Dialogue GEneration) requires models to produce trees o…
PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification data for Learning Enhanced generation
Sedrick Scott Keh, Kevin Lu, Varun Gangal +4
A personification is a figure of speech that endows inanimate entities with properties and actions typically seen as requiring animacy. In this paper, we explore the task of person…
The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding
Hao Fang, Anusha Balakrishnan, Harsh Jhamtani +7
In a real-world dialogue system, generated text must be truthful and informative while remaining fluent and adhering to a prescribed style. Satisfying these constraints simultaneou…
Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation
Prakhar Gupta, Harsh Jhamtani, Jeffrey P. Bigham
Target-guided response generation enables dialogue systems to smoothly transition a conversation from a dialogue context toward a target sentence. Such control is useful for design…
Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injection
Bodhisattwa Prasad Majumder, Harsh Jhamtani, Taylor Berg-Kirkpatrick +1
A limitation of current neural dialog models is that they tend to suffer from a lack of specificity and informativeness in generated responses, primarily due to dependence on train…
Truth-Conditional Captioning of Time Series Data
Harsh Jhamtani, Taylor Berg-Kirkpatrick
In this paper, we explore the task of automatically generating natural language descriptions of salient patterns in a time series, such as stock prices of a company over a week. A…
Investigating Robustness of Dialog Models to Popular Figurative Language Constructs
Harsh Jhamtani, Varun Gangal, Eduard Hovy +1
Humans often employ figurative language use in communication, including during interactions with dialog systems. Thus, it is important for real-world dialog systems to be able to h…
Unsupervised Enrichment of Persona-grounded Dialog with Background Stories
Bodhisattwa Prasad Majumder, Taylor Berg-Kirkpatrick, Julian McAuley +1
Humans often refer to personal narratives, life experiences, and events to make a conversation more engaging and rich. While persona-grounded dialog models are able to generate res…
Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation
Varun Gangal, Harsh Jhamtani, Eduard Hovy +1
Multiple different responses are often plausible for a given open domain dialog context. Prior work has shown the importance of having multiple valid reference responses for meanin…
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
Sebastian Gehrmann, Tosin Adewumi, Karmanya Aggarwal +53
We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of auto…
Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering
Harsh Jhamtani, Peter Clark
Despite the rapid progress in multihop question-answering (QA), models still have trouble explaining why an answer is correct, with limited explanation training data available to l…
Narrative Text Generation with a Latent Discrete Plan
Harsh Jhamtani, Taylor Berg-Kirkpatrick
Past work on story generation has demonstrated the usefulness of conditioning on a generation plan to generate coherent stories. However, these approaches have used heuristics or o…
Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions
Bodhisattwa Prasad Majumder, Harsh Jhamtani, Taylor Berg-Kirkpatrick +1
Existing persona-grounded dialog models often fail to capture simple implications of given persona descriptions, something which humans are able to do seamlessly. For example, stat…
Learning Rhyming Constraints using Structured Adversaries
Harsh Jhamtani, Sanket Vaibhav Mehta, Jaime Carbonell +1
Existing recurrent neural language models often fail to capture higher-level structure present in text: for example, rhyming patterns present in poetry. Much prior work on poetry g…
Learning to Describe Differences Between Pairs of Similar Images
Harsh Jhamtani, Taylor Berg-Kirkpatrick
In this paper, we introduce the task of automatically generating text to describe the differences between two similar images. We collect a new dataset by crowd-sourcing difference…