English
Related papers

Related papers: Is Inference Mediated by Distinct Semantic Structu…

200 papers

The question of what kinds of linguistic information are encoded in different layers of Transformer-based language models is of considerable interest for the NLP community. Existing work, however, has overwhelmingly focused on word-level…

Computation and Language · Computer Science 2023-10-19 Dmitry Nikolaev , Sebastian Padó

As language models (LMs) deliver increasing performance on a range of NLP tasks, probing classifiers have become an indispensable technique in the effort to better understand their inner workings. A typical setup involves (1) defining an…

Computation and Language · Computer Science 2024-08-01 Charles Jin , Martin Rinard

The field of mechanistic interpretability in pre-trained transformer models has demonstrated substantial evidence supporting the ''linear representation hypothesis'', which is the idea that high level concepts are encoded as vectors in the…

Machine Learning · Computer Science 2025-10-08 Damjan Kalajdzievski

Rigorous evaluation of the causal effects of semantic features on language model predictions can be hard to achieve for natural language reasoning problems. However, this is such a desirable form of analysis from both an interpretability…

Computation and Language · Computer Science 2024-04-04 Julia Rozanova , Marco Valentino , André Freitas

Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…

Machine Learning · Computer Science 2025-05-19 Omer Sahin Tas , Royden Wagner

Linear probes and sparse autoencoders consistently recover meaningful structure from transformer representations -- yet why should such simple methods succeed in deep, nonlinear systems? We show this is not merely an empirical regularity…

Machine Learning · Computer Science 2026-02-11 Andres Saurez , Yousung Lee , Dongsoo Har

Recent advances in mechanistic interpretability have revealed that large language models (LLMs) develop internal representations corresponding not only to concrete entities but also distinct, human-understandable abstract concepts and…

Machine Learning · Computer Science 2025-12-01 Rio Alexa Fear , Payel Mukhopadhyay , Michael McCabe , Alberto Bietti , Miles Cranmer

We present evidence that language models (LMs) of code can learn to represent the formal semantics of programs, despite being trained only to perform next-token prediction. Specifically, we train a Transformer model on a synthetic corpus of…

Machine Learning · Computer Science 2024-08-06 Charles Jin , Martin Rinard

Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured conceptual representations within these models, it remains unclear whether they functionally rely on…

Computation and Language · Computer Science 2026-04-21 Ningyu Xu , Qi Zhang , Xipeng Qiu , Xuanjing Huang

Word representations induced from models with discrete latent variables (e.g.\ HMMs) have been shown to be beneficial in many NLP applications. In this work, we exploit labeled syntactic dependency trees and formalize the induction problem…

Computation and Language · Computer Science 2016-02-08 Simon Šuster , Gertjan van Noord , Ivan Titov

Deep transformer models have pushed performance on NLP tasks to new limits, suggesting sophisticated treatment of complex linguistic inputs, such as phrases. However, we have limited understanding of how these models handle representation…

Computation and Language · Computer Science 2020-10-15 Lang Yu , Allyson Ettinger

Expressive text encoders such as RNNs and Transformer Networks have been at the center of NLP models in recent work. Most of the effort has focused on sentence-level tasks, capturing the dependencies between words in a single sentence, or…

Computation and Language · Computer Science 2021-09-15 Manuel Widmoser , Maria Leonor Pacheco , Jean Honorio , Dan Goldwasser

Much of the knowledge encoded in transformer language models (LMs) may be expressed in terms of relations: relations between words and their synonyms, entities and their attributes, etc. We show that, for a subset of relations, this…

Computation and Language · Computer Science 2024-02-19 Evan Hernandez , Arnab Sen Sharma , Tal Haklay , Kevin Meng , Martin Wattenberg , Jacob Andreas , Yonatan Belinkov , David Bau

Understanding the inner workings of Large Language Models (LLMs) is a critical research frontier. Prior research has shown that a single LLM's concept representations can be captured as steering vectors (SVs), enabling the control of LLM…

Computation and Language · Computer Science 2025-05-21 Youcheng Huang , Chen Huang , Duanyu Feng , Wenqiang Lei , Jiancheng Lv

Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across high-dimensional…

Machine Learning · Computer Science 2022-12-13 Yuxuan Li , James L. McClelland

Distributional semantics based on neural approaches is a cornerstone of Natural Language Processing, with surprising connections to human meaning representation as well. Recent Transformer-based Language Models have proven capable of…

Computation and Language · Computer Science 2022-04-04 Daniel Loureiro , Alípio Mário Jorge , Jose Camacho-Collados

Despite the remarkable success of Multimodal Large Language Models (MLLMs) across diverse tasks, the internal mechanisms governing how they encode and ground distinct visual concepts remain poorly understood. To bridge this gap, we propose…

Artificial Intelligence · Computer Science 2026-05-08 Zehao Deng , Tianjie Ju , Zheng Wu , Liangbo He , Jun Lan , Huijia Zhu , Weiqiang Wang , Zhuosheng Zhang

Causal transformer language models (LMs), such as GPT-3, typically require some form of positional encoding, such as positional embeddings. However, we show that LMs without any explicit positional encoding are still competitive with…

Computation and Language · Computer Science 2022-12-07 Adi Haviv , Ori Ram , Ofir Press , Peter Izsak , Omer Levy

Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One…

Computation and Language · Computer Science 2023-11-28 Haoyi Wu , Kewei Tu

Most modern computational approaches to lexical semantic change detection (LSC) rely on embedding-based distributional word representations with neural networks. Despite the strong performance on LSC benchmarks, they are often opaque. We…

Computation and Language · Computer Science 2026-05-05 Bach Phan-Tat , Kris Heylen , Dirk Geeraerts , Stefano De Pascale , Dirk Speelman
‹ Prev 1 2 3 10 Next ›