42 citations · 157 across the 17 of their papers we have counts for
18 papers
Rethinking Self-Distillation for Multi-Teacher Capability Merging
Roy Xie, Dan Friedman, Feng Nan +7
Combining capabilities of multiple expert models trained starting from the same base checkpoint has become increasingly common in frontier language-model post-training. Recent tren…
LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
Roy Xie, Dan Friedman, Donghan Yu +7
Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token sequences. Since VLM…
Extracting Rule-based Descriptions of Attention Features in Transformers
Dan Friedman, Adithya Bhaskar, Alexander Wettig +1
Mechanistic interpretability strives to explain model behavior in terms of bottom-up primitives. The leading paradigm is to express hidden states as a sparse linear combination of…
Continual Memorization of Factoids in Language Models
Howard Chen, Jiayi Geng, Adithya Bhaskar +2
As new knowledge rapidly accumulates, language models (LMs) with pretrained knowledge quickly become obsolete. A common approach to updating LMs is fine-tuning them directly on new…
Representing Rule-based Chatbots with Transformers
Dan Friedman, Abhishek Panigrahi, Danqi Chen
What kind of internal mechanisms might Transformers use to conduct fluid, natural-sounding conversations? Prior work has illustrated by construction how Transformers can solve vari…
Finding Transformer Circuits with Edge Pruning
Adithya Bhaskar, Alexander Wettig, Dan Friedman +1
The path to interpreting a language model often proceeds via analysis of circuits -- sparse computational subgraphs of the model that capture specific aspects of its behavior. Rece…
The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models
Adithya Bhaskar, Dan Friedman, Danqi Chen
Prior work has found that pretrained language models (LMs) fine-tuned with different random seeds can achieve similar in-domain performance but generalize differently on tests of s…
Interpretability Illusions in the Generalization of Simplified Models
Dan Friedman, Andrew Lampinen, Lucas Dixon +2
A common method to study deep learning systems is to use simplified model representations--for example, using singular value decomposition to visualize the model's hidden states in…
Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve
R. Thomas McCoy, Shunyu Yao, Dan Friedman +2
The widespread adoption of large language models (LLMs) makes it important to recognize their strengths and limitations. We argue that in order to develop a holistic understanding…
Learning Transformer Programs
Dan Friedman, Alexander Wettig, Danqi Chen
Recent research in mechanistic interpretability has attempted to reverse-engineer Transformer models by carefully inspecting network weights and activations. However, these approac…
Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations
Chenglei Si, Dan Friedman, Nitish Joshi +3
In-context learning (ICL) is an important paradigm for adapting large language models (LLMs) to new tasks, but the generalization behavior of ICL remains poorly understood. We inve…
Finding Dataset Shortcuts with Grammar Induction
Dan Friedman, Alexander Wettig, Danqi Chen
Many NLP datasets have been found to contain shortcuts: simple decision rules that achieve surprisingly high accuracy. However, it is difficult to discover shortcuts automatically.…
The Vendi Score: A Diversity Evaluation Metric for Machine Learning
Dan Friedman, Adji Bousso Dieng
Diversity is an important criterion for many areas of machine learning (ML), including generative modeling and dataset curation. However, existing metrics for measuring diversity a…
Single-dataset Experts for Multi-dataset Question Answering
Dan Friedman, Ben Dodge, Danqi Chen
Many datasets have been created for training reading comprehension models, and a natural question is whether we can combine them to build models that (1) perform better on all of t…
Factual Probing Is [MASK]: Learning vs. Learning to Recall
Zexuan Zhong, Dan Friedman, Danqi Chen
Petroni et al. (2019) demonstrated that it is possible to retrieve world facts from a pre-trained language model by expressing them as cloze-style prompts and interpret the model's…
ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks
Michihiro Yasunaga, Jungo Kasai, Rui Zhang +4
Scientific article summarization is challenging: large, annotated corpora are not available, and the summary should ideally include the article's impacts on research community. Thi…
Syntax-aware Neural Semantic Role Labeling with Supertags
Jungo Kasai, Dan Friedman, Robert Frank +2
We introduce a new syntax-aware model for dependency-based semantic role labeling that outperforms syntax-agnostic models for English and Spanish. We use a BiLSTM to tag the text w…
Deep density networks and uncertainty in recommender systems
Yoel Zeldes, Stavros Theodorakis, Efrat Solodnik +3
Building robust online content recommendation systems requires learning complex interactions between user preferences and content features. The field has evolved rapidly in recent…