Related papers: Why is Compiling Lifted Inference into a Low-Level…

Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction induction demonstrates that LLMs can infer better instructions with limited examples, existing…

Natural language free-text explanation generation is an efficient approach to train explainable language processing models for commonsense-knowledge-requiring tasks. The most predominant form of these models is the explain-then-predict…

Automating the translation of natural language to first-order logic (FOL) is crucial for knowledge representation and formal methods, yet remains challenging. We present a systematic evaluation of fine-tuned LLMs for this task, comparing…

When learning an input-output mapping from very few examples, is it better to first infer a latent function that explains the examples, or is it better to directly predict new test outputs, e.g. using a neural network? We study this…

Recent advances in large language models (LLMs) have shown that test-time scaling can substantially improve model performance on complex tasks, particularly in the coding domain. Under this paradigm, models use a larger token budget during…

We examine whether data generated by explanation techniques, which promote a process of self-reflection, can improve classifier performance. Our work is based on the idea that humans have the ability to make quick, intuitive decisions as…

Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they have learned over sequences of tokens influences their…

Large Language Models (LLMs) have attracted extensive attention due to their remarkable performance across various tasks. However, the substantial computational and memory requirements of LLM inference pose challenges for deployment in…

Recent progress in reasoning-oriented Large Language Models (LLMs) has been driven by introducing Chain-of-Thought (CoT) traces, where models generate intermediate reasoning traces before producing an answer. These traces, as in DeepSeek…

Recent advancements in data-to-text generation largely take on the form of neural end-to-end systems. Efforts have been dedicated to improving text generation systems by changing the order of training samples in a process known as…

Despite the effectiveness of utilizing the BERT model for document ranking, the high computational cost of such approaches limits their uses. To this end, this paper first empirically investigates the effectiveness of two knowledge…

Explaining why a language model produces a particular output requires local, input-level explanations. Existing methods uncover global capability circuits (e.g., indirect object identification), but not why the model answers a specific…

Modern sequential recommender systems commonly use transformer-based models for next-item prediction. While these models demonstrate a strong balance between efficiency and quality, integrating interleaving features - such as the query…

Reasoning-Intensive Retrieval (RIR) targets retrieval settings where relevance is mediated by latent inferential links between a query and supporting evidence, rather than semantic similarity. Motivated by the emergent reasoning abilities…

Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers and reports, they are not exposed to the reasoning processes…

Although large language models rely on chain-of-thought for complex reasoning, the overthinking phenomenon severely degrades inference efficiency. Existing reinforcement learning methods compress reasoning chains by designing elaborate…

A possible explanation for the impressive performance of masked language model (MLM) pre-training is that such models have learned to represent the syntactic structures prevalent in classical NLP pipelines. In this paper, we propose a…

We study the task of prompting large-scale language models to perform multi-step reasoning. Existing work shows that when prompted with a chain of thoughts (CoT), sequences of short sentences describing intermediate reasoning steps towards…

For information retrieval and binary classification, we show that precision at the top (or precision at k) and recall at the top (or recall at k) are maximised by thresholding the posterior probability of the positive class. This finding is…

While large language models (LLMs) such as ChatGPT and PaLM have demonstrated remarkable performance in various language understanding and generation tasks, their capabilities in complex reasoning and intricate knowledge utilization still…