相关论文: Deconstructing sentence disambiguation by joint la…

Large language models demonstrate strong problem-solving abilities through reasoning techniques such as chain-of-thought prompting and reflection. However, it remains unclear whether these reasoning capabilities extend to a form of social…

Recursive neural networks (RvNN) have been shown useful for learning sentence representations and helped achieve competitive performance on several natural language inference tasks. However, recent RvNN-based models fail to learn simple…

We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning trajectories as pseudo-gradient descent updates to the LLM's…

Paraphrases are texts that convey the same meaning while using different words or sentence structures. It can be used as an automatic data augmentation tool for many Natural Language Processing tasks, especially when dealing with…

We present a novel approach to efficiently learn a simultaneous translation model with coupled programmer-interpreter policies. First, wepresent an algorithmic oracle to produce oracle READ/WRITE actions for training bilingual…

When humans read a text, their eye movements are influenced by the structural complexity of the input sentences. This cognitive phenomenon holds across languages and recent studies indicate that multilingual language models utilize…

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Procrastination, the irrational delay of tasks, is a common occurrence in online learning. Potential negative consequences include higher risk of drop-outs, increased stress, and reduced mood. Due to the rise of learning management systems…

We present PaRTE, a collection of 1,126 pairs of Recognizing Textual Entailment (RTE) examples to evaluate whether models are robust to paraphrasing. We posit that if RTE models understand language, their predictions should be consistent…

Collectively, machine learning (ML) researchers are engaged in the creation and dissemination of knowledge about data-driven algorithms. In a given paper, researchers might aspire to any subset of the following goals, among others: to…

Math Word Problem (MWP) solving needs to discover the quantitative relationships over natural language narratives. Recent work shows that existing models memorize procedures from context and rely on shallow heuristics to solve MWPs. In this…

Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these…

A lack of corpora has so far limited advances in integrating human gaze data as a supervisory signal in neural attention mechanisms for natural language processing(NLP). We propose a novel hybrid text saliency model(TSM) that, for the first…

Neural machine translation (NMT) models are usually trained with the word-level loss using the teacher forcing algorithm, which not only evaluates the translation improperly but also suffers from exposure bias. Sequence-level training under…

Contrastive learning has been successfully used for retrieval of semantically aligned sentences, but it often requires large batch sizes or careful engineering to work well. In this paper, we instead propose a generative model for learning…

LLMs have demonstrated remarkable proficiency in understanding tasks but continue to struggle with long-context comprehension, particularly with content located in the middle of extensive inputs. This limitation, known as the…

Intuitively, human readers cope easily with errors in text; typos, misspelling, word substitutions, etc. do not unduly disrupt natural reading. Previous work indicates that letter transpositions result in increased reading times, but it is…

We address the question of repeatedly learning linear classifiers against agents who are strategically trying to game the deployed classifiers, and we use the Stackelberg regret to measure the performance of our algorithms. First, we show…

Numerous methods have been proposed to measure LLM misgendering, including probability-based evaluations (e.g., automatically with templatic sentences) and generation-based evaluations (e.g., with automatic heuristics or human validation).…

In this paper we leverage psychological methods to investigate LLMs' conceptual mastery in applying rules. We introduce a novel procedure to match the diversity of thought generated by LLMs to that observed in a human sample. We then…