相关论文: miniCTX: Neural Theorem Proving with (Long-)Contex…

Natural language inference (NLI) is a fundamental NLP task, investigating the entailment relationship between two texts. Popular NLI datasets present the task at sentence-level. While adequate for testing semantic representations, they fall…

Pretrained large Language Models (LLMs) are able to answer questions that are unlikely to have been encountered during training. However a diversity of potential applications exist in the broad domain of reasoning systems and considerations…

Leveraging mathematical Large Language Models (LLMs) for proof generation is a fundamental topic in LLMs research. We argue that the ability of current LLMs to prove statements largely depends on whether they have encountered the relevant…

Theory-of-Mind (ToM) ability possessed by Large Language Models (LLMs) has been shown to be limited. Most existing methods for improving ToM in LLMs adopt zero-shot prompting, and they face challenges including poor performance in complex…

Complex reasoning over text requires understanding and chaining together free-form predicates and logical connectives. Prior work has largely tried to do this either symbolically or with black-box transformers. We present a middle ground…

Topic modeling is a powerful technique for uncovering hidden themes within a collection of documents. However, the effectiveness of traditional topic models often relies on sufficient word co-occurrence, which is lacking in short texts.…

Theory of Mind (ToM), the ability to infer mental states in others, is pivotal for human social cognition. Existing evaluations of ToM in LLMs are largely limited to English, neglecting the linguistic diversity that shapes human cognition.…

Automated fact verification plays an essential role in fostering trust in the digital space. Despite the growing interest, the verification of temporal facts has not received much attention in the community. Temporal fact verification…

The use of continuous instead of discrete tokens during the Chain-of-Thought (CoT) phase of reasoning LLMs has garnered attention recently, based on the intuition that a continuous mixture of discrete tokens could simulate a superposition…

To break the context limits of large language models (LLMs) that bottleneck reasoning accuracy and efficiency, we propose the Thread Inference Model (TIM), a family of LLMs trained for recursive and decompositional problem solving, and…

The Axiom-Based Atlas is a novel framework that structurally represents mathematical theorems as proof vectors over foundational axiom systems. By mapping the logical dependencies of theorems onto vectors indexed by axioms - such as those…

Pre-training models with large crawled corpora can lead to issues such as toxicity and bias, as well as copyright and privacy concerns. A promising way of alleviating such concerns is to conduct pre-training with synthetic tasks and data,…

The study explores whether current Large Language Models (LLMs) exhibit Theory of Mind (ToM) capabilities -- specifically, the ability to infer others' beliefs, intentions, and emotions from text. Given that LLMs are trained on language…

Techniques in which words are represented as vectors have proved useful in many applications in computational linguistics, however there is currently no general semantic formalism for representing meaning in terms of vectors. We present a…

The unprecedented surge in video data production in recent years necessitates efficient tools to extract meaningful frames from videos for downstream tasks. Long-term temporal reasoning is a key desideratum for frame retrieval systems.…

Large language models (LLMs) enable researchers to analyze text at unprecedented scale and minimal cost. Researchers can now revisit old questions and tackle novel ones with rich data. We provide an econometric framework for realizing this…

Large language models are increasingly capable at closed-world mathematical reasoning, but research assistance also requires source-grounded use of the literature. When a proof reaches a non-trivial step, a useful assistant should determine…

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Neural sequence models, especially transformers, exhibit a remarkable capacity for in-context learning. They can construct new predictors from sequences of labeled examples $(x, f(x))$ presented in the input without further parameter…

Although large language models (LLMs) have tremendous utility, trustworthiness is still a chief concern: models often generate incorrect information with high confidence. While contextual information can help guide generation, identifying…