221 citations · 461 across the 29 of their papers we have counts for
30 papers
Let Me Teach You: Pedagogical Foundations of Feedback for Language Models
Beatriz Borges, Niket Tandon, Tanja Käser +1
Natural Language Feedback (NLF) is an increasingly popular mechanism for aligning Large Language Models (LLMs) to human preferences. Despite the diversity of the information it can…
Aligning Language Models to User Opinions
EunJeong Hwang, Bodhisattwa Prasad Majumder, Niket Tandon
An important aspect of developing LLMs that interact with humans is to align models' behavior to their users. It is possible to prompt an LLM into behaving as a certain persona, es…
Editing Common Sense in Transformers
Anshita Gupta, Debanjan Mondal, Akshay Krishna Sheshadri +4
Editing model parameters directly in Transformers makes updating open-source transformer-based models possible without re-training (Meng et al., 2023). However, these editing metho…
OpenPI2.0: An Improved Dataset for Entity Tracking in Texts
Li Zhang, Hainiu Xu, Abhinav Kommula +2
Much text describes a changing world (e.g., procedures, stories, newswires), and understanding them requires tracking how entities change. An earlier dataset, OpenPI, provided crow…
RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs
Afra Feyza Akyürek, Ekin Akyürek, Aman Madaan +4
Despite their unprecedented success, even the largest language models make mistakes. Similar to how humans learn and improve using feedback, previous work proposed providing langua…
Self-Refine: Iterative Refinement with Self-Feedback
Aman Madaan, Niket Tandon, Prakhar Gupta +13
Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an…
Conditional set generation using Seq2seq models
Aman Madaan, Dheeraj Rajagopal, Niket Tandon +2
Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set g…
Memory-assisted prompt editing to improve GPT-3 after deployment
Aman Madaan, Niket Tandon, Peter Clark +1
Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to humans. For example, GPT-3 would mistakenly interpret "What word is similar to good?" to mean a ho…
Interscript: A dataset for interactive learning of scripts through error feedback
Niket Tandon, Aman Madaan, Peter Clark +2
How can an end-user provide feedback if a deployed structured prediction model generates inconsistent output, ignoring the structural complexity of human language? This is an emerg…
Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedback
Niket Tandon, Aman Madaan, Peter Clark +1
Large language models (LMs), while powerful, are not immune to mistakes, but can be difficult to retrain. Our goal is for an LM to continue to improve after deployment, without ret…
Think about it! Improving defeasible reasoning by first modeling the question scenario
Aman Madaan, Niket Tandon, Dheeraj Rajagopal +3
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence. Existing cognitive science literature on defeasible reasoning…
Could you give me a hint? Generating inference graphs for defeasible reasoning
Aman Madaan, Dheeraj Rajagopal, Niket Tandon +2
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence. A commonly used method in cognitive science and logic literat…
Improving Neural Model Performance through Natural Language Feedback on Their Explanations
Aman Madaan, Niket Tandon, Dheeraj Rajagopal +4
A class of explainable NLP models for reasoning tasks support their decisions by generating free-form or structured explanations, but what happens when these supporting structures…
proScript: Partially Ordered Scripts Generation via Pre-trained Language Models
Keisuke Sakaguchi, Chandra Bhagavatula, Ronan Le Bras +3
Scripts - standardized event sequences describing typical everyday activities - have been shown to help understand narratives by providing expectations, resolving ambiguity, and fi…
CURIE: An Iterative Querying Approach for Reasoning About Situations
Dheeraj Rajagopal, Aman Madaan, Niket Tandon +5
Recently, models have been shown to predict the effects of unexpected situations, e.g., would cloudy skies help or hinder plant growth? Given a context, the goal of such situationa…
A Dataset for Tracking Entities in Open Domain Procedural Text
Niket Tandon, Keisuke Sakaguchi, Bhavana Dalvi Mishra +5
We present the first dataset for tracking state changes in procedural text from arbitrary domains by using an unrestricted (open) vocabulary. For example, in a text describing fog…
Do Dogs have Whiskers? A New Knowledge Base of hasPart Relations
Sumithra Bhakthavatsalam, Kyle Richardson, Niket Tandon +1
We present a new knowledge-base of hasPart relationships, extracted from a large corpus of generic statements. Complementary to other resources available, it is the first which is…
What-if I ask you to explain: Explaining the effects of perturbations in procedural text
Dheeraj Rajagopal, Niket Tandon, Bhavana Dalvi +2
We address the task of explaining the effects of perturbations in procedural text, an important test of process comprehension. Consider a passage describing a rabbit's life-cycle:…
Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text
Bhavana Dalvi Mishra, Niket Tandon, Antoine Bosselut +2
Our goal is to better comprehend procedural text, e.g., a paragraph about photosynthesis, by not only predicting what happens, but why some actions need to happen before others. Ou…
WIQA: A dataset for "What if..." reasoning over procedural text
Niket Tandon, Bhavana Dalvi Mishra, Keisuke Sakaguchi +2
We introduce WIQA, the first large-scale dataset of "What if..." questions over procedural text. WIQA contains three parts: a collection of paragraphs each describing a process, e.…
Know2Look: Commonsense Knowledge for Visual Search
Sreyasi Nag Chowdhury, Niket Tandon, Gerhard Weikum
With the rise in popularity of social media, images accompanied by contextual text form a huge section of the web. However, search and retrieval of documents are still largely depe…
VISIR: Visual and Semantic Image Label Refinement
Sreyasi Nag Chowdhury, Niket Tandon, Hakan Ferhatosmanoglu +1
The social media explosion has populated the Internet with a wealth of images. There are two existing paradigms for image retrieval: 1) content-based image retrieval (CBIR), which…
From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project
Peter Clark, Oren Etzioni, Daniel Khashabi +11
AI has achieved remarkable mastery over games such as Chess, Go, and Poker, and even Jeopardy, but the rich variety of standardized exams has remained a landmark challenge. Even in…
Be Consistent! Improving Procedural Text Comprehension using Label Consistency
Xinya Du, Bhavana Dalvi Mishra, Niket Tandon +4
Our goal is procedural text comprehension, namely tracking how the properties of entities (e.g., their location) change with time given a procedural text (e.g., a paragraph about p…