2.4k citations · 3k across the 56 of their papers we have counts for
44 papers · 1 filter
Copy-Paste Language Models
Nathan Godey, Yoav Artzi
Transformers are intuitively considered to be efficient at copying from their inputs. We actually show that the ability of LLMs to copy in context can be improved through explicit…
Co-Evolving Structured Knowledge and Reasoning in Language Models
Ryan Thomas Noonan, Linxi Zhao, Menghan Xu +6
Retrieval-augmented methods improve factual accuracy by grounding language models in external knowledge, but retrieving over unstructured text often introduces irrelevant context a…
CT: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees
S M Rafiuddin, Atriya Sen
Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a branching reply tree. We study…
Co-LMLM: Continuous-Query Limited Memory Language Models
Yair Feldman, Linxi Zhao, Nathan Godey +5
Externalizing knowledge in LLM pre-training is a promising avenue to achieve higher performance at smaller scales, control knowledge use, and overall increase model transparency. W…
The State-Prediction Separation Hypothesis
Giovanni Monea, Nathan Godey, Kianté Brantley +1
Transformers use the same forward computation stream to both predict the next token and store useful state for future token predictions. We formulate the \emph{state-prediction sep…
Lost in Backpropagation: The LM Head is a Gradient Bottleneck
Nathan Godey, Yoav Artzi
The last layer of neural language models (LMs) projects output features of dimension to logits in dimension , the size of the vocabulary, where usually . This misma…
Success and Cost Elicit Convention Formation for Efficient Communication
Saujas Vaduguru, Yilun Hua, Yoav Artzi +1
Humans leverage shared conversational context to become increasingly successful and efficient at communicating over time. One manifestation of this is the formation of ad hoc lingu…
No Mean Feat: Simple, Strong Baselines for Context Compression
Yair Feldman, Yoav Artzi
Context compression reduces Transformer inference costs by replacing lengthy inputs with shorter pre-computed representations. It carries significant benefits for retrieval-augment…
Breadcrumbs Reasoning: Memory-Efficient Reasoning with Compression Beacons
Giovanni Monea, Yair Feldman, Shankar Padmanabhan +2
The scalability of large language models for long-context reasoning is severely constrained by the linear growth of their Transformer key-value cache, which incurs significant memo…
Ad hoc conventions generalize to new referents
Anya Ji, Claire Augusta Bergey, Ron Eliav +2
How do people talk about things they've never talked about before? One view suggests that a new shared naming system establishes an arbitrary link to a specific target, like proper…
Post-training for Efficient Communication via Convention Formation
Yilun Hua, Evan Wang, Yoav Artzi
Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions. In contrast, prior work shows that LLMs do not…
Pre-training Limited Memory Language Models with Internal and External Knowledge
Linxi Zhao, Sofian Zalouk, Christian K. Belardi +7
Neural language models are black-boxes--both linguistic patterns and factual knowledge are distributed across billions of opaque parameters. This entangled encoding makes it diffic…
Cancer Type, Stage and Prognosis Assessment from Pathology Reports using LLMs
Rachit Saluja, Jacob Rosenthal, Yoav Artzi +3
Large Language Models (LLMs) have shown significant promise across various natural language processing tasks. However, their application in the field of pathology, particularly for…
Retrospective Learning from Interactions
Zizhao Chen, Mustafa Omer Gul, Yiwei Chen +3
Multi-turn interactions between large language models (LLMs) and users naturally include implicit feedback signals. If an LLM responds in an unexpected way to an instruction, the u…
LLMs Are In-Context Bandit Reinforcement Learners
Giovanni Monea, Antoine Bosselut, Kianté Brantley +1
Large Language Models (LLMs) excel at in-context learning (ICL), a supervised learning technique that relies on adding annotated examples to the model context. We investigate a con…
CoGen: Learning from Feedback with Coupled Comprehension and Generation
Mustafa Omer Gul, Yoav Artzi
Systems with both language comprehension and generation capabilities can benefit from the tight connection between the two. This work studies coupling comprehension and generation…
Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs
Yilun Hua, Yoav Artzi
Humans spontaneously use increasingly efficient language as interactions progress, by adapting and forming ad-hoc conventions. This phenomenon has been studied extensively using re…
A Joint Study of Phrase Grounding and Task Performance in Vision and Language Models
Noriyuki Kojima, Hadar Averbuch-Elor, Yoav Artzi
Key to tasks that require reasoning about natural language in visual contexts is grounding words and phrases to image regions. However, observing this grounding in contemporary mod…
Semantic uncertainty guides the extension of conventions to new referents
Ron Eliav, Anya Ji, Yoav Artzi +1
A long tradition of studies in psycholinguistics has examined the formation and generalization of ad hoc conventions in reference games, showing how newly acquired conventions for…
Continually Improving Extractive QA via Human Feedback
Ge Gao, Hung-Ting Chen, Yoav Artzi +1
We study continually improving an extractive question answering (QA) system via human user feedback. We design and deploy an iterative approach, where information-seeking users ask…
Continual Learning for Instruction Following from Realtime Feedback
Alane Suhr, Yoav Artzi
We propose and deploy an approach to continually train an instruction-following agent from feedback provided by users during collaborative interactions. During interaction, human u…
Abstract Visual Reasoning with Tangram Shapes
Anya Ji, Noriyuki Kojima, Noah Rush +4
We introduce KiloGram, a resource for studying abstract visual reasoning in humans and machines. Drawing on the history of tangram puzzles as stimuli in cognitive science, we build…
Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages
Felix Wu, Kwangyoun Kim, Shinji Watanabe +4
We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete repres…
Simulating Bandit Learning from User Feedback for Extractive Question Answering
Ge Gao, Eunsol Choi, Yoav Artzi
We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze…