565 citations · 2.5k across the 94 of their papers we have counts for
21 papers · 1 filter
Semantics and Spatiality of Emergent Communication
Rotem Ben Zion, Boaz Carmeli, Orr Paradise +1
When artificial agents are jointly trained to perform collaborative tasks using a communication channel, they develop opaque goal-oriented communication protocols. Good task perfor…
Growing a Tail: Increasing Output Diversity in Large Language Models
Michal Shur-Ofry, Bar Horowitz-Amsalem, Adir Rahamim +1
How diverse are the outputs of large language models when diversity is desired? We examine the diversity of responses of several language models to questions with multiple possible…
Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods
Tsachi Blau, Moshe Kimhi, Yonatan Belinkov +2
Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates…
Distinguishing Ignorance from Error in LLM Hallucinations
Adi Simhi, Jonathan Herzig, Idan Szpektor +1
Large language models (LLMs) are susceptible to hallucinations -- factually incorrect outputs -- leading to a large body of work on detecting and mitigating such cases. We argue th…
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
Yaniv Nikankin, Anja Reusch, Aaron Mueller +1
Do large language models (LLMs) solve reasoning tasks by learning robust generalizable algorithms, or do they memorize training data? To investigate this question, we use arithmeti…
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
Hadas Orgad, Michael Toker, Zorik Gekhman +4
Large language models (LLMs) often produce errors, including factual inaccuracies, biases, and reasoning failures, collectively referred to as "hallucinations". Recent studies have…
Fast Forwarding Low-Rank Training
Adir Rahamim, Naomi Saphra, Sara Kangaslahti +1
Parameter efficient finetuning methods like low-rank adaptation (LoRA) aim to reduce the computational costs of finetuning pretrained Language Models (LMs). Enabled by these low-ra…
Jamba-1.5: Hybrid Transformer-Mamba Models at Scale
Jamba Team, Barak Lenz, Alan Arazi +58
We present Jamba-1.5, new instruction-tuned large language models based on our Jamba architecture. Jamba is a hybrid Transformer-Mamba mixture of experts architecture, providing hi…
Confidence Regulation Neurons in Language Models
Alessandro Stolfo, Ben Wu, Wes Gurnee +4
Despite their widespread use, the mechanisms by which large language models (LLMs) represent and regulate uncertainty in next-token predictions remain largely unexplored. This stud…
REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space
Tomer Ashuach, Martin Tutek, Yonatan Belinkov
Language models (LMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns. Current ap…
DEPTH: Discourse Education through Pre-Training Hierarchically
Zachary Bamberger, Ofek Glick, Chaim Baskin +1
Language Models (LMs) struggle with linguistic understanding at the discourse level, even though discourse patterns such as coherence, cohesion, and narrative flow are prevalent in…
Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
Shadi Iskander, Kira Radinsky, Yonatan Belinkov
Mitigating social biases typically requires identifying the social groups associated with each data sample. In this paper, we present DAFair, a novel approach to address social bia…
Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs
Adi Simhi, Jonathan Herzig, Idan Szpektor +1
Large language models (LLMs) are prone to hallucinations, which sparked a widespread effort to detect and prevent them. Recent work attempts to mitigate hallucinations by interveni…
Concept-Best-Matching: Evaluating Compositionality in Emergent Communication
Boaz Carmeli, Yonatan Belinkov, Ron Meir
Artificial agents that learn to communicate in order to accomplish a given task acquire communication protocols that are typically opaque to a human. A large body of work has attem…
Jamba: A Hybrid Transformer-Mamba Language Model
Opher Lieber, Barak Lenz, Hofit Bata +19
We present Jamba, a new base large language model based on a novel hybrid Transformer-Mamba mixture-of-experts (MoE) architecture. Specifically, Jamba interleaves blocks of Transfo…
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
Samuel Marks, Can Rager, Eric J. Michaud +3
We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model b…
Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
Michael Hanna, Sandro Pezzelle, Yonatan Belinkov
Many recent language model (LM) interpretability studies have adopted the circuits framework, which aims to find the minimal computational subgraph, or circuit, that explains LM be…
Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines
Michael Toker, Hadas Orgad, Mor Ventura +2
Text-to-image diffusion models (T2I) use a latent representation of a text prompt to guide the image generation process. However, the process by which the encoder produces the text…
Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
Nikhil Prakash, Tamar Rott Shaham, Tal Haklay +2
Fine-tuning on generalized tasks such as instruction following, code generation, and mathematics has been shown to enhance language models' performance on a range of tasks. Neverth…
Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
Shahar Katz, Yonatan Belinkov, Mor Geva +1
Understanding how Transformer-based Language Models (LMs) learn and recall information is a key goal of the deep learning community. Recent interpretability methods project weights…
Accelerating the Global Aggregation of Local Explanations
Alon Mor, Yonatan Belinkov, Benny Kimelfeld
Local explanation methods highlight the input tokens that have a considerable impact on the outcome of classifying the document at hand. For example, the Anchor algorithm applies a…