5 citations · 6 across the 7 of their papers we have counts for
8 papers
Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?
Ayan Antik Khan, Harsh Kohli, Yuekun Yao +2
Mechanistic interpretability has made substantial progress in automatically localizing circuits, but explaining what localized components do remains labor-intensive and difficult t…
Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers
Harsh Kohli, Srinivasan Parthasarathy, Huan Sun +1
We study implicit reasoning, i.e. the ability to combine knowledge or rules within a single forward pass. While transformer-based large language models store substantial factual kn…
How Lexical is Bilingual Lexicon Induction?
Harsh Kohli, Helian Feng, Nicholas Dronen +3
In contemporary machine learning approaches to bilingual lexicon induction (BLI), a model learns a mapping between the embedding spaces of a language pair. Recently, retrieve-and-r…
GroundCocoa: A Benchmark for Evaluating Compositional & Conditional Reasoning in Language Models
Harsh Kohli, Sachin Kumar, Huan Sun
The rapid progress of large language models (LLMs) has seen them excel and frequently surpass human performance on standard benchmarks. This has enabled many downstream application…
Learning Representations for Zero-Shot Retrieval over Structured Data
Harsh Kohli
Large Scale Question-Answering systems today are widely used in downstream applications such as chatbots and conversational dialogue agents. Typically, such systems consist of an A…
Training Mixed-Objective Pointing Decoders for Block-Level Optimization in Search Recommendation
Harsh Kohli
Related or ideal follow-up suggestions to a web query in search engines are often optimized based on several different parameters -- relevance to the original query, diversity, cli…
Training Bi-Encoders for Word Sense Disambiguation
Harsh Kohli
Modern transformer-based neural architectures yield impressive results in nearly every NLP task and Word Sense Disambiguation, the problem of discerning the correct sense of a word…
Transfer Learning and Augmentation for Word Sense Disambiguation
Harsh Kohli
Many downstream NLP tasks have shown significant improvement through continual pre-training, transfer learning and multi-task learning. State-of-the-art approaches in Word Sense Di…