25 citations · 31 across the 10 of their papers we have counts for
14 papers
How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling
Dhananjay Ashok, Shantanu Agarwal, Vivek Datla +2
World models (WMs) simulate the transition dynamics of environments, enabling agents to plan over the consequences of their actions. In text-based environments, fine-tuning a Langu…
GameBoyWorlds: A Testbed for Self-Improvement in Embodied Video Games
Dhananjay Ashok, Adam Shen, Aslan Huo Feng +10
Powered by expert guidance, agents can operate in interactive environments; however, it is unclear whether they can learn autonomously from their own experience. To evaluate such s…
Toward Interactive Understanding of Code APIs
Dhananjay Ashok, Jesse Thomason, Jonathan May
Empowered by advances in Language Model agents, systems have made substantial strides in code generation and understanding. However, these approaches often rely on read access to t…
Seamless Deception: Larger Language Models Are Better Knowledge Concealers
Dhananjay Ashok, Ruth-Ann Armstrong, Jonathan May
Language Models (LMs) may acquire harmful knowledge, and yet feign ignorance of these topics when under audit. Inspired by the recent discovery of deception-related behaviour patte…
A Representation Sharpening Framework for Zero Shot Dense Retrieval
Dhananjay Ashok, Suraj Nair, Mutasem Al-Darabsah +3
Zero-shot dense retrieval is a challenging setting where a document corpus is provided without relevant queries, necessitating a reliance on pretrained dense retrievers (DRs). Howe…
Can VLMs Recall Factual Associations From Visual References?
Dhananjay Ashok, Ashutosh Chaubey, Hirona J. Arai +2
Through a controlled study, we identify a systematic deficiency in the multimodal grounding of Vision Language Models (VLMs). While VLMs can recall factual associations when provid…
Language Models Can Predict Their Own Behavior
Dhananjay Ashok, Jonathan May
The text produced by language models (LMs) can exhibit specific `behaviors,' such as a failure to follow alignment training, that we hope to detect and react to during deployment.…
A Little Human Data Goes A Long Way
Dhananjay Ashok, Jonathan May
Faced with an expensive human annotation process, creators of NLP systems increasingly turn to synthetic data generation. While this method shows promise, the extent to which synth…
Controllable Text Generation in the Instruction-Tuning Era
Dhananjay Ashok, Barnabas Poczos
While most research on controllable text generation has focused on steering base Language Models, the emerging instruction-tuning and prompting paradigm offers an alternate approac…
FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines
Matthew Barker, Emma Kallina, Dhananjay Ashok +6
Even though machine learning (ML) pipelines affect an increasing array of stakeholders, there is little work on how input from stakeholders is recorded and incorporated. We propose…
PromptNER: Prompting For Named Entity Recognition
Dhananjay Ashok, Zachary C. Lipton
In a surprising turn, Large Language Models (LLMs) together with a growing arsenal of prompt-based heuristics now offer powerful off-the-shelf approaches providing few-shot solutio…
SciFix: Outperforming GPT3 on Scientific Factual Error Correction
Dhananjay Ashok, Atharva Kulkarni, Hai Pham +1
Due to the prohibitively high cost of creating error correction datasets, most Factual Claim Correction methods rely on a powerful verification model to guide the correction proces…
A Solver + Gradient Descent Training Algorithm for Deep Neural Networks
Dhananjay Ashok, Vineel Nagisetty, Christopher Srinivasa +1
We present a novel hybrid algorithm for training Deep Neural Networks that combines the state-of-the-art Gradient Descent (GD) method with a Mixed Integer Linear Programming (MILP)…
Logic Guided Genetic Algorithms
Dhananjay Ashok, Joseph Scott, Sebastian Wetzel +2
We present a novel Auxiliary Truth enhanced Genetic Algorithm (GA) that uses logical or mathematical constraints as a means of data augmentation as well as to compute loss (in conj…