English
Related papers

Related papers: How often are errors in natural language reasoning…

200 papers

Large language models (LLMs) have achieved widespread success on a variety of in-context few-shot tasks, but this success is typically evaluated via correctness rather than consistency. We argue that self-consistency is an important…

Computation and Language · Computer Science 2024-02-09 Angelica Chen , Jason Phang , Alicia Parrish , Vishakh Padmakumar , Chen Zhao , Samuel R. Bowman , Kyunghyun Cho

Neural network language models can serve as computational hypotheses about how humans process language. We compared the model-human consistency of diverse language models using a novel experimental approach: controversial sentence pairs.…

Computation and Language · Computer Science 2023-09-15 Tal Golan , Matthew Siegelman , Nikolaus Kriegeskorte , Christopher Baldassano

Large language models (LLMs) are prone to hallucinations and sensitive to prompt perturbations, often resulting in inconsistent or unreliable generated text. Different methods have been proposed to mitigate such hallucinations and…

Computation and Language · Computer Science 2025-11-25 Xiaoyuan Wu , Weiran Lin , Omer Akgul , Lujo Bauer

We evaluate the robustness of several large language models on multiple datasets. Robustness here refers to the relative insensitivity of the model's answers to meaning-preserving variants of their input. Benchmark datasets are constructed…

Computation and Language · Computer Science 2024-11-05 Samuel Ackerman , Ella Rabinovich , Eitan Farchi , Ateret Anaby-Tavor

Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought prompting that elicits verbalized reasoning. However, LLMs often generate text with obvious…

Artificial Intelligence · Computer Science 2024-12-06 Zhihui Xie , Jizhou Guo , Tong Yu , Shuai Li

Pretrained language models can be queried for factual knowledge, with potential applications in knowledge base acquisition and tasks that require inference. However, for that, we need to know how reliable this knowledge is, and recent work…

Computation and Language · Computer Science 2024-04-05 Constanza Fierro , Anders Søgaard

While neural models show remarkable accuracy on individual predictions, their internal beliefs can be inconsistent across examples. In this paper, we formalize such inconsistency as a generalization of prediction error. We propose a…

Artificial Intelligence · Computer Science 2019-09-16 Tao Li , Vivek Gupta , Maitrey Mehta , Vivek Srikumar

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

Semantic consistency of a language model is broadly defined as the model's ability to produce semantically-equivalent outputs, given semantically-equivalent inputs. We address the task of assessing question-answering (QA) semantic…

Computation and Language · Computer Science 2023-11-03 Ella Rabinovich , Samuel Ackerman , Orna Raz , Eitan Farchi , Ateret Anaby-Tavor

As large language models (LLMs) are increasingly deployed in high-stakes applications, robust uncertainty estimation is essential for ensuring the safe and trustworthy deployment of LLMs. We present the most comprehensive study to date of…

Computation and Language · Computer Science 2025-06-02 Linwei Tao , Yi-Fan Yeh , Minjing Dong , Tao Huang , Philip Torr , Chang Xu

Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local inconsistency, where a…

Computation and Language · Computer Science 2025-12-22 Riad Ahmed Anonto , Md Labid Al Nahiyan , Md Tanvir Hassan

In recent years, large language models (LLMs) have demonstrated significant success in performing varied natural language tasks such as language translation, question-answering, summarizing, fact-checking, etc. Despite LLMs' impressive…

Computation and Language · Computer Science 2025-03-03 Bishwamittra Ghosh , Sarah Hasan , Naheed Anjum Arafat , Arijit Khan

Results reported in large-scale multilingual evaluations are often fragmented and confounded by factors such as target languages, differences in experimental setups, and model choices. We propose a framework that disentangles these…

Computation and Language · Computer Science 2025-08-26 Songbo Hu , Ivan Vulić , Anna Korhonen

Large language models (LLMs) achieve strong average performance yet remain unreliable at the instance level, with frequent hallucinations, brittle failures, and poorly calibrated confidence. We study reliability through the lens of…

Artificial Intelligence · Computer Science 2026-01-13 Pranav Kallem

In noisy environments, speech can be hard to understand for humans. Spoken dialog systems can help to enhance the intelligibility of their output, either by modifying the speech synthesis (e.g., imitate Lombard speech) or by optimizing the…

Computation and Language · Computer Science 2022-10-20 Anupama Chingacham , Vera Demberg , Dietrich Klakow

Large language models (LLMs) are increasingly being used for tasks where outputs shape human decisions, so it is critical to verify that their responses consistently reflect desired human values. Humans, as individuals or groups, don't…

Artificial Intelligence · Computer Science 2026-01-16 Aman Gupta , Denny O'Shea , Fazl Barez

Paraphrase generation is a pivotal task in natural language processing (NLP). Existing datasets in the domain lack syntactic and lexical diversity, resulting in paraphrases that closely resemble the source sentences. Moreover, these…

Computation and Language · Computer Science 2024-04-19 Lasal Jayawardena , Prasan Yapa

We investigate a long-perceived shortcoming in the typical use of BLEU: its reliance on a single reference. Using modern neural paraphrasing techniques, we study whether automatically generating additional diverse references can provide…

Computation and Language · Computer Science 2020-10-12 Rachel Bawden , Biao Zhang , Lisa Yankovskaya , Andre Tättar , Matt Post

Given the increasingly prominent role NLP models (will) play in our lives, it is important for human expectations of model behavior to align with actual model behavior. Using Natural Language Inference (NLI) as a case study, we investigate…

Computation and Language · Computer Science 2021-09-20 Grusha Prasad , Yixin Nie , Mohit Bansal , Robin Jia , Douwe Kiela , Adina Williams

Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address. They tend to produce generations that (i) rely too much on copying from the context, (ii) contain repetitions…

Computation and Language · Computer Science 2020-05-07 Margaret Li , Stephen Roller , Ilia Kulikov , Sean Welleck , Y-Lan Boureau , Kyunghyun Cho , Jason Weston