English
Related papers

Related papers: Polysemanticity or Polysemy? Lexical Identity Conf…

200 papers

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

Machine Learning · Computer Science 2023-10-05 Hoagy Cunningham , Aidan Ewart , Logan Riggs , Robert Huben , Lee Sharkey

Comparing the internal representations of neural networks is a central goal in both neuroscience and machine learning. Standard alignment metrics operate on raw neural activations, implicitly assuming that similar representations produce…

Machine Learning · Computer Science 2026-04-02 Sunny Liu , Habon Issa , André Longon , Liv Gorton , Meenakshi Khosla , David Klindt

The present study uses a computational approach to examine the role of semantic constraints in normal reading. This methodology avoids confounds inherent in conventional measures of predictability, allowing for theoretically deeper accounts…

Computation and Language · Computer Science 2019-12-24 Markus J. Hofmann , Mareike A. Kleemann , Andre Roelke , Christian Vorstius , Ralph Radach

Interpretability research often adopts a neuron-centric lens, treating individual neurons as the fundamental units of explanation. However, neuron-level explanations can be undermined by superposition, where single units respond to mixtures…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Julien Colin , Lore Goetschalckx , Thomas Fel , Victor Boutin , Thomas Serre , Nuria Oliver

The superposition hypothesis states that single neurons may participate in representing multiple features in order for the neural network to represent more features than it has neurons. In neuroscience and AI, representational alignment…

Machine Learning · Computer Science 2025-11-14 André Longon , David Klindt , Meenakshi Khosla

This paper explores techniques that focus on understanding and resolving ambiguity in language within the field of natural language processing (NLP), highlighting the complexity of linguistic phenomena such as polysemy and homonymy and…

Computation and Language · Computer Science 2024-03-26 Miuru Abeysiriwardana , Deshan Sumanathilaka

Superposition or Neuron Polysemanticity are important concepts in the field of interpretability and one might say they are these most intricately beautiful blockers in our path of decoding the Machine Learning black-box. The idea behind…

Machine Learning · Computer Science 2024-12-24 Akanksha Devkar

Subword tokenizers trained on multilingual corpora naturally produce overlapping tokens across languages. Does token overlap facilitate cross-lingual transfer or instead introduce interference between languages? Prior work offers mixed…

Computation and Language · Computer Science 2025-09-26 Julie Kallini , Dan Jurafsky , Christopher Potts , Martijn Bartelds

Language-specific neurons in LLMs that strongly correlate with individual languages have been shown to influence model behavior by deactivating them. However, their role in amplification remains underexplored. This work investigates the…

Polysemantic neurons -- neurons that activate for a set of unrelated features -- have been seen as a significant obstacle towards interpretability of task-optimized deep networks, with implications for AI safety. The classic origin story of…

Machine Learning · Computer Science 2024-02-14 Victor Lecomte , Kushal Thaman , Rylan Schaeffer , Naomi Bashkansky , Trevor Chow , Sanmi Koyejo

Isolated word meanings are inherently uncertain. This uncertainty reduces when they are combined and anchored in context. We propose that grammar compresses meaning uncertainty cross-linguistically, which is reflected in brain and…

There has been a considerable amount of work on uncertainty in knowledge-based systems. This work has generally been concerned with uncertainty arising from the strength of inferences and the weight of evidence. In this paper we discuss…

Artificial Intelligence · Computer Science 2013-04-12 Steven J. Henkind

Large Language Models (LLMs) achieve strong linguistic performance, yet their internal mechanisms for producing these predictions remain unclear. We investigate the hypothesis that LLMs encode representations of linguistic constraint…

Computation and Language · Computer Science 2026-05-15 Hardy , Sebastian Padó

Commonsense reasoning is intuitive for humans but has been a long-term challenge for artificial intelligence (AI). Recent advancements in pretrained language models have shown promising results on several commonsense benchmark datasets.…

Computation and Language · Computer Science 2021-06-03 Shikhar Singh , Nuan Wen , Yu Hou , Pegah Alipoormolabashi , Te-Lin Wu , Xuezhe Ma , Nanyun Peng

Neural networks often pack many unrelated concepts into a single neuron - a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. This paper provides a toy model where polysemanticity can be…

Word similarities affect language acquisition and use in a multi-relational way barely accounted for in the literature. We propose a multiplex network representation of this mental lexicon of word similarities as a natural framework for…

Physics and Society · Physics 2018-01-23 Massimo Stella , Nicole M. Beckage , Markus Brede , Manlio De Domenico

Neural networks achieve remarkable performance through superposition: encoding multiple features as overlapping directions in activation space rather than dedicating individual neurons to each feature. This challenges interpretability, yet…

Machine Learning · Computer Science 2025-12-16 Leonard Bereska , Zoe Tzifa-Kratira , Reza Samavi , Efstratios Gavves

Large language models (LLMs) are known to be sensitive to input phrasing, but the mechanisms by which semantic cues shape reasoning remain poorly understood. We investigate this phenomenon in the context of comparative math problems with…

Computation and Language · Computer Science 2025-06-05 Mohammadamin Shafiei , Hamidreza Saffari , Nafise Sadat Moosavi

Large language models (LLMs) reason over discrete token ID sequences, yet modern subword tokenizers routinely produce non-unique encodings: multiple token ID sequences can detokenize to identical surface strings. This representational…

Computation and Language · Computer Science 2026-01-22 Navid Ayoobi , Marcus I Armstrong , Arjun Mukherjee

Pervasive polysemanticity in large language models (LLMs) undermines discrete neuron-concept attribution, posing a significant challenge for model interpretation and control. We systematically analyze both encoder and decoder based LLMs…

Machine Learning · Computer Science 2026-04-13 Muhammad Umair Haider , Hammad Rizwan , Hassan Sajjad , Peizhong Ju , A. B. Siddique
‹ Prev 1 2 3 10 Next ›