Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features
Aleksandr Beznosikov
David Dobre
A self-attention-based CNN-Bi-LSTM model for accurate state-of-charge estimation of lithium-ion batteries
Zeinab Sherkatghanad
Amin Ghazanfari
SelfIE: Self-Interpretation of Large Language Model Embeddings
Haozhe Chen
Carl Vondrick
How do large language models (LLMs) obtain their answers? The ability to explain and control an LLM's reasoning process is key for reliabili… (see more)ty, transparency, and future model developments. We propose SelfIE (Self-Interpretation of Embeddings), a framework that enables LLMs to interpret their own embeddings in natural language by leveraging their ability to respond to inquiries about a given passage. Capable of interpreting open-world concepts in the hidden embeddings, SelfIE reveals LLM internal reasoning in cases such as making ethical decisions, internalizing prompt injection, and recalling harmful knowledge. SelfIE's text descriptions on hidden embeddings also open up new avenues to control LLM reasoning. We propose Supervised Control, which allows editing open-ended concepts while only requiring gradient computation of individual layer. We extend RLHF to hidden embeddings and propose Reinforcement Control that erases harmful knowledge in LLM without supervision targets.
Stealing part of a production language model
Nicholas Carlini
Daniel Paleka
Krishnamurthy Dj Dvijotham
Thomas Steinke
Jonathan Hayase
A. Feder Cooper
Katherine Lee
Matthew Jagielski
Milad Nasr
Arthur Conmy
Eric Wallace
Florian Tramèr
We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like … (see more)OpenAI's ChatGPT or Google's PaLM-2. Specifically, our attack recovers the embedding projection layer (up to symmetries) of a transformer model, given typical API access. For under \\
Stochastic positional embeddings improve masked image modeling
Amir Bar
Florian Bordes
Assaf Shocher
Mahmoud Assran
Nicolas Ballas
Trevor Darrell
Amir Globerson
Yann LeCun
Masked Image Modeling (MIM) is a promising self-supervised learning approach that enables learning from unlabeled images. Despite its recent… (see more) success, learning good representations through MIM remains challenging because it requires predicting the right semantic content in accurate locations. For example, given an incomplete picture of a dog, we can guess that there is a tail, but we cannot determine its exact location. In this work, we propose to incorporate location uncertainty into MIM by using stochastic positional embeddings (StoP). Specifically, we condition the model on stochastic masked token positions drawn from a Gaussian distribution. StoP reduces overfitting to location features and guides the model toward learning features that are more robust to location uncertainties. Quantitatively, StoP improves downstream MIM performance on a variety of downstream tasks, including
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
Jesse Farebrother
Jordi Orbay
Quan Vuong
Adrien Ali Taiga
Yevgen Chebotar
Ted Xiao
Alex Irpan
Sergey Levine
Aleksandra Faust
Aviral Kumar
Rishabh Agarwal
Towards Modular LLMs by Building and Reusing a Library of LoRAs
Oleksiy Ostapenko
Zhan Su
Edoardo Ponti
Matheus Pereira
Lucas Caccia
Do Transformer World Models Give Better Policy Gradients?
Michel Ma
Tianwei Ni
Clement Gehring
Pierluca D'Oro
Unsupervised Concept Discovery Mitigates Spurious Correlations
Md Rifat Arefin
Yan Zhang
Aristide Baratin
Francesco Locatello
Dianbo Liu
Kenji Kawaguchi
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
Massimo Caccia
Issam Hadj Laradji
Manuel Del Verme
Tom Marty
Léo Boisvert
Megh Thakkar
David Vazquez
Alexandre Lacoste
Sequential predictive learning is a unifying theory for hippocampal representation and replay
Daniel Levenstein
Aleksei Efremov
Roy Henha Eyono
Adrien Peyrache
The mammalian hippocampus contains a cognitive map that represents an animal’s position in the environment 1 and generates offline “repl… (see more)ay” 2,3 for the purposes of recall 4, planning 5,6, and forming long term memories 7. Recently, it’s been found that artificial neural networks trained to predict sensory inputs develop spatially tuned cells 8, aligning with predictive theories of hippocampal function 9–11. However, whether predictive learning can also account for the ability to produce offline replay is unknown. Here, we find that spatially tuned cells, which robustly emerge from all forms of predictive learning, do not guarantee the presence of a cognitive map with the ability to generate replay. Offline simulations only emerged in networks that used recurrent connections and head-direction information to predict multi-step observation sequences, which promoted the formation of a continuous attractor reflecting the geometry of the environment. These offline trajectories were able to show wake-like statistics, autonomously replay recently experienced locations, and could be directed by a virtual head direction signal. Further, we found that networks trained to make cyclical predictions of future observation sequences were able to rapidly learn a cognitive map and produced sweeping representations of future positions reminiscent of hippocampal theta sweeps 12. These results demonstrate how hippocampal-like representation and replay can emerge in neural networks engaged in predictive learning, and suggest that hippocampal theta sequences reflect a circuit that implements a data-efficient algorithm for sequential predictive learning. Together, this framework provides a unifying theory for hippocampal functions and hippocampal-inspired approaches to artificial intelligence.
Comparing LLM prompting with Cross-lingual transfer performance on Indigenous and Low-resource Brazilian Languages
A. Seza Dougruoz
Andr'e Coneglian
Atul Kr. Ojha
Large Language Models are transforming NLP for a variety of tasks. However, how LLMs perform NLP tasks for low-resource languages (LRLs) is … (see more)less explored. In line with the goals of the AmericasNLP workshop, we focus on 12 LRLs from Brazil, 2 LRLs from Africa and 2 high-resource languages (HRLs) (e.g., English and Brazilian Portuguese). Our results indicate that the LLMs perform worse for the part of speech (POS) labeling of LRLs in comparison to HRLs. We explain the reasons behind this failure and provide an error analysis through examples observed in our data set.