50 citations · 106 across the 7 of their papers we have counts for
9 papers
Does self-distillation improve reasoning?
Jason Ken Adhinarta, Raina Wu, Ashutosh Sharma +5
Self-distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as correct answers or environmental fe…
AI Steerability 360: A Toolkit for Steering Large Language Models
Erik Miehling, Karthikeyan Natesan Ramamurthy, Praveen Venkateswaran +10
The AI Steerability 360 toolkit is an extensible, open-source Python library for steering LLMs. Steering abstractions are designed around four model control surfaces: input (modifi…
DeepVoting: Learning and Fine-Tuning Voting Rules with Canonical Embeddings
Leonardo Matone, Ben Abramowitz, Ben Armstrong +2
Aggregating agent preferences into a collective decision is an important step in many problems (e.g., hiring, elections, peer review) and across areas of computer science (e.g., re…
Learning Global Transparent Models Consistent with Local Contrastive Explanations
Tejaswini Pedapati, Avinash Balakrishnan, Karthikeyan Shanmugam +1
There is a rich and growing literature on producing local contrastive/counterfactual explanations for black-box models (e.g. neural networks). In these methods, for an input, an ex…
Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks
Pavan Kapanipathi, Veronika Thost, Siva Sankalp Patel +10
Textual entailment is a fundamental task in natural language processing. Most approaches for solving the problem use only the textual content present in training data. A few approa…
Model Agnostic Contrastive Explanations for Structured Data
Amit Dhurandhar, Tejaswini Pedapati, Avinash Balakrishnan +3
Recently, a method [7] was proposed to generate contrastive explanations for differentiable models such as deep neural networks, where one has complete access to the model. In this…
Word Mover's Embedding: From Word2Vec to Document Embedding
Lingfei Wu, Ian E. H. Yen, Kun Xu +5
While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised…
Incorporating Behavioral Constraints in Online AI Systems
Avinash Balakrishnan, Djallel Bouneffouf, Nicholas Mattei +1
AI systems that learn through reward feedback about the actions they take are increasingly deployed in domains that have significant impact on our daily life. However, in many case…
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
Abhishek Kumar, Prasanna Sattigeri, Avinash Balakrishnan
Disentangled representations, where the higher level data generative factors are reflected in disjoint latent dimensions, offer several benefits such as ease of deriving invariant…