相关论文: Evolved preambles for MAX-SAT heuristics

Many capable large language models (LLMs) are developed via self-supervised pre-training followed by a reinforcement-learning fine-tuning phase, often based on human or AI feedback. During this stage, models may be guided by their inductive…

The challenges of solving complex university-level mathematics problems, particularly those from MIT, and Columbia University courses, and selected tasks from the MATH dataset, remain a significant obstacle in the field of artificial…

We propose a version of WalkSAT algorithm, named as BetaWalkSAT. This method uses probabilistic reasoning for biasing the starting state of the local search algorithm. Beta distribution is used to model the belief over boolean values of the…

A new account of parameter setting during grammatical acquisition is presented in terms of Generalized Categorial Grammar embedded in a default inheritance hierarchy, providing a natural partial ordering on the setting of parameters.…

Gradual semantics with abstract argumentation provide each argument with a score reflecting its acceptability, i.e. how "much" it is attacked by other arguments. Many different gradual semantics have been proposed in the literature, each…

We introduce a neural semantic parser that converts natural language utterances to intermediate representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target…

Existing NLP datasets contain various biases, and models tend to quickly learn those biases, which in turn limits their robustness. Existing approaches to improve robustness against dataset biases mostly focus on changing the training…

We present an extremely simple polynomial-space exponential-time $(1-\varepsilon)$-approximation algorithm for MAX-k-SAT that is (slightly) faster than the previous known polynomial-space $(1-\varepsilon)$-approximation algorithms by Hirsch…

Generative language models (LMs) are increasingly used for document class-prediction tasks and promise enormous improvements in cost and efficiency. Existing research often examines simple classification tasks, but the capability of LMs to…

Optimization plays an important role in tackling public health problems. Animal instincts can be used effectively to solve complex public health management issues by providing optimal or approximately optimal solutions to complicated…

Solving an optimization task in any domain is a very challenging problem, especially when dealing with nonlinear problems and non-convex functions. Many meta-heuristic algorithms are very efficient when solving nonlinear functions. A…

Multilingual pre-trained models are known to suffer from the curse of multilinguality, which causes per-language performance to drop as they cover more languages. We address this issue by introducing language-specific modules, which allows…

Heuristic design with large language models (LLMs) has emerged as a promising approach for tackling combinatorial optimization problems (COPs). However, existing approaches often rely on manually predefined evolutionary computation (EC)…

Human reasoning involves different strategies, each suited to specific problems. Prior work shows that large language model (LLMs) tend to favor a single reasoning strategy, potentially limiting their effectiveness in diverse reasoning…

Randomized algorithms for deciding satisfiability were shown to be effective in solving problems with thousands of variables. However, these algorithms are not complete. That is, they provide no guarantee that a satisfying assignment, if…

Regular signed SAT is a variant of the well-known satisfiability problem in which the variables can take values in a fixed set V \subset [0,1], and the `literals' have the form "x \le a" or "x \ge a". We answer some open question regarding…

Although large language models (LLMs) have demonstrated remarkable proficiency in modeling text and generating human-like text, they may exhibit biases acquired from training data in doing so. Specifically, LLMs may be susceptible to a…

In the problem of active sequential hypothesis testing (ASHT), a learner seeks to identify the true hypothesis from among a known set of hypotheses. The learner is given a set of actions and knows the random distribution of the outcome of…

Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and…

A recent trend in artificial intelligence is the use of pretrained models for language and vision tasks, which have achieved extraordinary performance but also puzzling failures. Probing these models' abilities in diverse ways is therefore…