English
Related papers

Related papers: Testing the Ability of Language Models to Interpre…

200 papers

Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks. However, their opaqueness and proliferation into scientific domains such as neuroscience have created a growing…

Computation and Language · Computer Science 2024-05-28 Vinamra Benara , Chandan Singh , John X. Morris , Richard Antonello , Ion Stoica , Alexander G. Huth , Jianfeng Gao

Question answering (QA) in natural language (NL) has been an important aspect of AI from its early days. Winograd's ``councilmen'' example in his 1972 paper and McCarthy's Mr. Hug example of 1976 highlights the role of external knowledge in…

Computation and Language · Computer Science 2020-03-10 Chitta Baral , Pratyay Banerjee , Kuntal Kumar Pal , Arindam Mitra

Recent NLP literature has seen growing interest in improving model interpretability. Along this direction, we propose a trainable neural network layer that learns a global interaction graph between words and then selects more informative…

Computation and Language · Computer Science 2023-02-07 Arshdeep Sekhon , Hanjie Chen , Aman Shrivastava , Zhe Wang , Yangfeng Ji , Yanjun Qi

Large Language Models offer impressive language capabilities but suffer from well-known limitations, including hallucinations, biases, privacy concerns, and high computational costs. These issues are largely driven by the combination of…

Computation and Language · Computer Science 2025-09-03 Jaime Collado-Montañez , L. Alfonso Ureña-López , Arturo Montejo-Ráez

While NLP models often seek to capture cognitive states via language, the validity of predicted states is determined by comparing them to annotations created without access the cognitive states of the authors. In behavioral sciences,…

Computation and Language · Computer Science 2025-02-20 Vasudha Varadarajan , Syeda Mahwish , Xiaoran Liu , Julia Buffolino , Christian C. Luhmann , Ryan L. Boyd , H. Andrew Schwartz

While large language models have shown exciting progress on several NLP benchmarks, evaluating their ability for complex analogical reasoning remains under-explored. Here, we introduce a high-quality crowdsourced dataset of narratives for…

Computation and Language · Computer Science 2022-05-18 Sayan Ghosh , Shashank Srivastava

Having an intelligent dialogue agent that can engage in conversational question answering (ConvQA) is now no longer limited to Sci-Fi movies only and has, in fact, turned into a reality. These intelligent agents are required to understand…

Computation and Language · Computer Science 2023-04-17 Munazza Zaib , Quan Z. Sheng , Wei Emma Zhang , Adnan Mahmood

We study feature interactions in the context of feature attribution methods for post-hoc interpretability. In interpretability research, getting to grips with feature interactions is increasingly recognised as an important challenge,…

Computation and Language · Computer Science 2023-06-22 Jaap Jumelet , Willem Zuidema

Despite the recent success of deep neural networks in natural language processing (NLP), their interpretability remains a challenge. We analyze the representations learned by neural machine translation models at various levels of…

Computation and Language · Computer Science 2019-11-04 Yonatan Belinkov , Nadir Durrani , Fahim Dalvi , Hassan Sajjad , James Glass

Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition. However, limited study has been done on large language models' capability to perform conceptual reasoning. In…

Computation and Language · Computer Science 2024-04-02 Ben Zhou , Hongming Zhang , Sihao Chen , Dian Yu , Hongwei Wang , Baolin Peng , Dan Roth , Dong Yu

How language-agnostic are current state-of-the-art NLP tools? Are there some types of language that are easier to model with current methods? In prior work (Cotterell et al., 2018) we attempted to address this question for language…

Computation and Language · Computer Science 2020-02-26 Sabrina J. Mielke , Ryan Cotterell , Kyle Gorman , Brian Roark , Jason Eisner

There is an ongoing debate in the NLP community whether modern language models contain linguistic knowledge, recovered through so-called probes. In this paper, we study whether linguistic knowledge is a necessary condition for the good…

Computation and Language · Computer Science 2022-01-04 Vassilina Nikoulina , Maxat Tezekbayev , Nuradil Kozhakhmet , Madina Babazhanova , Matthias Gallé , Zhenisbek Assylbekov

Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP. By overcoming data sparsity problems, as well as providing information about semantic relatedness which is not…

Computation and Language · Computer Science 2014-03-21 Karl Moritz Hermann , Phil Blunsom

Can language models (LM) ground question-answering (QA) tasks in the knowledge base via inherent relational reasoning ability? While previous models that use only LMs have seen some success on many QA tasks, more recent methods include…

Computation and Language · Computer Science 2023-06-07 Yujie Lu , Siqi Ouyang , Kairui Zhou

The performance of Large language models (LLMs) across a broad range of domains has been impressive but have been critiqued as not being able to reason about their process and conclusions derived. This is to explain the conclusions draw,…

Computation and Language · Computer Science 2024-10-30 Rob Sullivan , Nelly Elsayed

Probing and enhancing large language models' reasoning capacity remains a crucial open question. Here we re-purpose the reverse dictionary task as a case study to probe LLMs' capacity for conceptual inference. We use in-context learning to…

Computation and Language · Computer Science 2024-02-27 Ningyu Xu , Qi Zhang , Menghan Zhang , Peng Qian , Xuanjing Huang

Indirectness is a common feature of daily communication, yet is underexplored in NLP research for both low-resource as well as high-resource languages. Indirect Question Answering (IQA) aims at classifying the polarity of indirect answers.…

Computation and Language · Computer Science 2026-04-28 Miriam Winkler , Verena Blaschke , Barbara Plank

Language models are typically applied at the sentence level, without access to the broader document context. We present a neural language model that incorporates document context in the form of a topic model-like architecture, thus…

Computation and Language · Computer Science 2017-10-16 Jey Han Lau , Timothy Baldwin , Trevor Cohn

Large language models (LLMs) need to serve everyone, including a global majority of non-English speakers. However, most LLMs today, and open LLMs in particular, are often intended for use in just English (e.g. Llama2, Mistral) or a small…

Computation and Language · Computer Science 2024-07-19 Carolin Holtermann , Paul Röttger , Timm Dill , Anne Lauscher

Natural Language Processing (NLP) has become one of the leading application areas in the current Artificial Intelligence boom. Transfer learning has enabled large deep learning neural networks trained on the language modeling task to vastly…

Computation and Language · Computer Science 2022-06-16 Csaba Veres