English
Related papers

Related papers: Eliciting Latent Predictions from Transformers wit…

200 papers

In this paper, we evaluate the capability of transformer-based language models in making inferences over uncertain text that includes uncertain rules of reasoning. We cover both Pre-trained Language Models (PLMs) and generative Large…

Computation and Language · Computer Science 2024-02-12 Aliakbar Nafar , Kristen Brent Venable , Parisa Kordjamshidi

Lattices are compact representations that encode multiple hypotheses, such as speech recognition results or different word segmentations. It is shown that encoding lattices as opposed to 1-best results generated by automatic speech…

Computation and Language · Computer Science 2020-11-03 Chao-Wei Huang , Yun-Nung Chen

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Gabriele Merlin , Vedant Nanda , Ruchit Rawal , Mariya Toneva

People are regularly confronted with potentially deceptive statements (e.g., fake news, misleading product reviews, or lies about activities). Only few works on automated text-based deception detection have exploited the potential of deep…

Computation and Language · Computer Science 2022-10-07 Loukas Ilias , Felix Soldner , Bennett Kleinberg

We study the evolution of latent space in fine-tuned NLP models. Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations. More specifically, we discover latent concepts in the…

Computation and Language · Computer Science 2022-10-25 Nadir Durrani , Hassan Sajjad , Fahim Dalvi , Firoj Alam

Transformer language models have achieved state-of-the-art performance for a variety of natural language tasks but have been shown to encode unwanted biases. We evaluate the social biases encoded by transformers trained with the masked…

Computation and Language · Computer Science 2025-08-19 Rahul Zalkikar , Kanchan Chandra

We analyze the operation of transformer language adapters, which are small modules trained on top of a frozen language model to adapt its predictions to new target languages. We show that adapted predictions mostly evolve in the source…

Computation and Language · Computer Science 2024-06-11 Jesujoba O. Alabi , Marius Mosbach , Matan Eyal , Dietrich Klakow , Mor Geva

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or…

Computation and Language · Computer Science 2026-03-24 Lorenzo Noci , Gregor Bachmann , Seyed-Mohsen Moosavi-Dezfooli , Moin Nabi

Logit Lens is a widely adopted method for mechanistic interpretability of transformer-based language models, enabling the analysis of how internal representations evolve across layers by projecting them into the output vocabulary space.…

Computer Vision and Pattern Recognition · Computer Science 2025-04-24 Ryota Takatsuki , Sonia Joseph , Ippei Fujisawa , Ryota Kanai

Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a…

Computation and Language · Computer Science 2019-09-05 Marjan Ghazvininejad , Omer Levy , Yinhan Liu , Luke Zettlemoyer

In natural language processing, current methods for understanding Transformers are successful at identifying intermediate predictions during a model's inference. However, these approaches function as limited diagnostic checkpoints, lacking…

Machine Learning · Computer Science 2025-12-18 Aditya Gupta , Kirandeep Kaur , Vinayak Gupta , Chirag Shah

Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn…

Computation and Language · Computer Science 2022-10-28 Liliang Ren , Zixuan Zhang , Han Wang , Clare R. Voss , Chengxiang Zhai , Heng Ji

We conjecture that hidden state vectors corresponding to individual input tokens encode information sufficient to accurately predict several tokens ahead. More concretely, in this paper we ask: Given a hidden (internal) representation of a…

Computation and Language · Computer Science 2024-03-14 Koyena Pal , Jiuding Sun , Andrew Yuan , Byron C. Wallace , David Bau

Despite the extensive success of pretrained language models as encoders for building NLP systems, they haven't seen prominence as decoders for sequence generation tasks. We explore the question of whether these models can be adapted to be…

Computation and Language · Computer Science 2020-08-21 Nishant Subramani , Nivedita Suresh

Recent research has demonstrated that transformers, particularly linear attention models, implicitly execute gradient-descent-like algorithms on data provided in-context during their forward inference step. However, their capability in…

Machine Learning · Computer Science 2024-10-31 Max Vladymyrov , Johannes von Oswald , Mark Sandler , Rong Ge

Generating semantically coherent text requires a robust internal representation of linguistic structures, which traditional embedding techniques often fail to capture adequately. A novel approach, Latent Lexical Projection (LLP), is…

Computation and Language · Computer Science 2025-03-26 Ziad Shaker , Brendan Ashdown , Hugo Fitzalan , Alistair Heathcote , Jocasta Huntington

Predicting upcoming events is critical to our ability to interact with our environment. Transformer models, trained on next-word prediction, appear to construct representations of linguistic input that can support diverse downstream tasks.…

Computation and Language · Computer Science 2023-11-10 Eghbal A. Hosseini , Evelina Fedorenko

Large pre-trained language models (PLMs) have demonstrated strong performance on natural language understanding (NLU) tasks through fine-tuning. However, fine-tuned models still suffer from overconfident predictions, especially in…

Computation and Language · Computer Science 2023-05-31 Guande He , Jianfei Chen , Jun Zhu

Recent advances in training vision-language models have demonstrated unprecedented robustness and transfer learning effectiveness; however, standard computer vision datasets are image-only, and therefore not well adapted to such training…

Computer Vision and Pattern Recognition · Computer Science 2023-02-22 Andre Nakkab , Benjamin Feuer , Chinmay Hegde

Pre-trained large language models based on Transformers have demonstrated remarkable in-context learning (ICL) abilities. With just a few demonstration examples, the models can implement new tasks without any parameter updates. However, it…

Machine Learning · Computer Science 2024-11-04 Ruifeng Ren , Yong Liu