Related papers: Proof Artifact Co-training for Theorem Proving wit…

We investigate how large language models can be used as research tools in scientific computing while preserving mathematical rigor. We propose a human-in-the-loop workflow for interactive theorem proving and discovery with LLMs. Human…

The aim in imitation learning is to learn effective policies by utilizing near-optimal expert demonstrations. However, high-quality demonstrations from human experts can be expensive to obtain in large numbers. On the other hand, it is…

As neural theorem provers become increasingly agentic, the ability to interpret and act on compiler feedback is critical. However, existing Lean datasets consist almost exclusively of correct proofs, offering little supervision for…

Large language models (LLMs) remain unreliable for high-stakes claim verification due to hallucinations and shallow reasoning. While retrieval-augmented generation (RAG) and multi-agent debate (MAD) address this, they are limited by…

Person-job fit is an essential part of online recruitment platforms in serving various downstream applications like Job Search and Candidate Recommendation. Recently, pretrained large language models have further enhanced the effectiveness…

Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, yet they often struggle with maintaining factual accuracy, particularly in knowledge-intensive domains like healthcare. This study…

Translation has played a crucial role in improving the performance on multilingual tasks: (1) to generate the target language data from the source language data for training and (2) to generate the source language data from the target…

Supervised fine-tuning (SFT) with token-level hard labels can amplify overconfident imitation of factually unsupported targets, causing hallucinations that propagate in multi-sentence generation. We study an augmented SFT setting in which…

Theorem proving in natural mathematical language - the mixture of symbolic and natural language used by humans - plays a central role in mathematical advances and education, and tests aspects of reasoning that are core to intelligence. Yet…

Large language models (LLMs) have shown great promise in machine translation, but they still struggle with contextually dependent terms, such as new or domain-specific words. This leads to inconsistencies and errors that are difficult to…

Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including most recently language modeling and reasoning. To demystify…

The Chain-of-Thought (CoT) paradigm, while enhancing the interpretability of Large Language Models (LLMs), is constrained by the inefficiencies and expressive limits of natural language. Latent Chain-of-Thought (latent CoT) reasoning, which…

Large language models like GPT-4 exhibit emergent capabilities across general-purpose tasks, such as basic arithmetic, when trained on extensive text data, even though these tasks are not explicitly encoded by the unsupervised, next-token…

Formal reasoning and automated theorem proving constitute a challenging subfield of machine learning, in which machines are tasked with proving mathematical theorems using formal languages like Lean. A formal verification system can check…

Improving large language model (LLM) reasoning requires supervision that is both aligned with the model's own test-time states and informative at the token level. Reinforcement learning with verifiable rewards provides on-policy exploration…

Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…

Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support…

Multi-task learning promises better model generalization on a target task by jointly optimizing it with an auxiliary task. However, the current practice requires additional labeling efforts for the auxiliary task, while not guaranteeing…

Many recent language models (LMs) are capable of in-context learning (ICL), manifested in the LMs' ability to perform a new task solely from natural-language instruction. Previous work curating in-context learners assumes that ICL emerges…

This work presents In-Context Policy Iteration, an algorithm for performing Reinforcement Learning (RL), in-context, using foundation models. While the application of foundation models to RL has received considerable attention, most…