72 citations · 289 across the 69 of their papers we have counts for
21 papers · 1 filter
Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
Michael Y. Hu, Aaron Mueller, Candace Ross +7
The BabyLM Challenge is a community effort to close the data-efficiency gap between human and computational language learners. Participants compete to optimize language model train…
Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation
Shivalika Singh, Angelika Romanou, Clémentine Fourrier +21
Cultural biases in multilingual datasets pose significant challenges for their effectiveness as global benchmarks. These biases stem not only from differences in language but also…
ZipNN: Lossless Compression for AI Models
Moshik Hershcovitch, Andrew Wood, Leshem Choshen +7
With the growth of model sizes and the scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While th…
Model merging with SVD to tie the Knots
George Stoica, Pratik Ramesh, Boglarka Ecsedi +2
Recent model merging methods demonstrate that the parameters of fully-finetuned models specializing in distinct tasks can be combined into one model capable of solving all tasks wi…
The Future of Open Human Feedback
Shachar Don-Yehiya, Ben Burtenshaw, Ramon Fernandez Astudillo +17
Human feedback on conversations with language language models (LLMs) is central to how these systems learn about the world, improve their capabilities, and are steered toward desir…
Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs
Maxim Ifergan, Leshem Choshen, Roee Aharoni +2
The veracity of a factoid is largely independent of the language it is written in. However, language models are inconsistent in their ability to answer the same factual question ac…
Data Contamination Report from the 2024 CONDA Shared Task
Oscar Sainz, Iker García-Ferrero, Alon Jacovi +25
The 1st Workshop on Data Contamination (CONDA 2024) focuses on all relevant aspects of data contamination in natural language processing, where data contamination is understood as…
The ShareLM Collection and Plugin: Contributing Human-Model Chats for the Benefit of the Community
Shachar Don-Yehiya, Leshem Choshen, Omri Abend
Human-model conversations provide a window into users' real-world scenarios, behavior, and needs, and thus are a valuable resource for model development and research. While for-pro…
A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning
Prateek Yadav, Colin Raffel, Mohammed Muqeeth +6
The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particular domain or task. Model MoErging methods…
Do These LLM Benchmarks Agree? Fixing Benchmark Evaluation with BenchBench
Yotam Perlitz, Ariel Gera, Ofir Arviv +5
Recent advancements in Language Models (LMs) have catalyzed the creation of multiple benchmarks, designed to assess these models' general capabilities. A crucial task, however, is…
Naturally Occurring Feedback is Common, Extractable and Useful
Shachar Don-Yehiya, Leshem Choshen, Omri Abend
Human feedback data is a critical component in developing language models. However, collecting this feedback is costly and ultimately not scalable. Inspired by the way human interl…
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
Rickard Brüel-Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj +4
Fine-tuning large language models (LLMs) with low-rank adaptations (LoRAs) has become common practice, often yielding numerous copies of the same LLM differing only in their LoRA u…
Efficient multi-prompt evaluation of LLMs
Felipe Maia Polo, Ronald Xu, Lucas Weber +6
Most popular benchmarks for comparing LLMs rely on a limited set of prompt templates, which may not fully capture the LLMs' abilities and can affect the reproducibility of results…
Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models
Anna A. Ivanova, Aalok Sathe, Benjamin Lipkin +17
The ability to build and reason about models of the world is essential for situated language understanding. But evaluating world modeling capabilities in modern AI systems -- espec…
Holmes: A Benchmark to Assess the Linguistic Competence of Language Models
Andreas Waldis, Yotam Perlitz, Leshem Choshen +2
We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence - their unconscious understanding of linguistic phenomena. Specifically, we use…
[Call for Papers] The 2nd BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus
Leshem Choshen, Ryan Cotterell, Michael Y. Hu +7
After last year's successful BabyLM Challenge, the competition will be hosted again in 2024/2025. The overarching goals of the challenge remain the same; however, some of the compe…
Asymmetry in Low-Rank Adapters of Foundation Models
Jiacheng Zhu, Kristjan Greenewald, Kimia Nadjahi +6
Parameter-efficient fine-tuning optimizes large, pre-trained foundation models by updating a subset of parameters; in this class, Low-Rank Adaptation (LoRA) is particularly effecti…
tinyBenchmarks: evaluating LLMs with fewer examples
Felipe Maia Polo, Lucas Weber, Leshem Choshen +3
The versatility of large language models (LLMs) led to the creation of diverse benchmarks that thoroughly test a variety of language models' abilities. These benchmarks consist of…
Genie: Achieving Human Parity in Content-Grounded Datasets Generation
Asaf Yehudai, Boaz Carmeli, Yosi Mass +5
The lack of high-quality data for content-grounded generation tasks has been identified as a major obstacle to advancing these tasks. To address this gap, we propose Genie, a novel…
Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI
Elron Bandel, Yotam Perlitz, Elad Venezian +9
In the dynamic landscape of generative NLP, traditional text processing pipelines limit research flexibility and reproducibility, as they are tailored to specific dataset, task, an…
Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability
Afra Feyza Akyürek, Ekin Akyürek, Leshem Choshen +2
While language models (LMs) can sometimes generate factually correct text and estimate truth values of individual claims, these generally do not reflect a globally coherent, manipu…