Related papers: Reverse Training to Nurse the Reversal Curse

Large language models (LLMs) have achieved remarkable success in machine translation, demonstrating impressive performance across diverse languages. However, translationese, characterized by overly literal and unnatural translations,…

A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight into the underlying cognitive mechanisms. While neural network models trained on large-scale behavioral data often…

Language models typically tokenize raw text into sequences of subword identifiers from a predefined vocabulary, a process inherently sensitive to typographical errors, length variations, and largely oblivious to the internal structure of…

The capabilities of large language models (LLMs) are widely regarded as relying on autoregressive models (ARMs). We challenge this notion by introducing LLaDA, a diffusion model trained from scratch under the pre-training and supervised…

Reverse Engineering (RE) is central to software security, enabling tasks such as vulnerability discovery and malware analysis, but it remains labor-intensive and requires substantial expertise. Earlier advances in deep learning start to…

Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones. However, this assumption ignores the potential benefits of using the full…

Large Language Models (LLMs) have demonstrated impressive capabilities in creative tasks such as storytelling and E-mail generation. However, as LLMs are primarily trained on final text results rather than intermediate revisions, it might…

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…

This research addresses a fundamental question in AI: whether large language models truly understand concepts or simply recognize patterns. The authors propose bidirectional reasoning,the ability to apply transformations in both directions…

We introduce compression laws for language language models (LLMs). While recent scaling laws have sought to understand how LLMs scale with respect to model size, pre-training data, and computational resources, we focus on understanding how…

Recent studies have shown that as Transformer-based language models become larger and are trained on very large amounts of data, the fit of their surprisal estimates to naturalistic human reading times degrades. The current work presents a…

Optimizing training performance in large language models (LLMs) remains an essential challenge, particularly in improving model performance while maintaining computational costs. This work challenges the conventional approach of training…

The curse of multilinguality phenomenon is a fundamental problem of multilingual Large Language Models (LLMs), where the competition between massive languages results in inferior performance. It mainly comes from limited capacity and…

We introduce a method to address goal misgeneralization in reinforcement learning (RL), leveraging Large Language Model (LLM) feedback during training. Goal misgeneralization, a type of robustness failure in RL occurs when an agent retains…

Inverse tasks can uncover potential reasoning gaps as Large Language Models (LLMs) scale up. In this work, we explore the redefinition task, in which we assign alternative values to well-known physical constants and units of measure,…

With the advent of Large Language Models (LLMs), generating rule-based data for real-world applications has become more accessible. Due to the inherent ambiguity of natural language and the complexity of rule sets, especially in long…

Recent large language models have been trained on vast datasets, but also often on repeated data, either intentionally for the purpose of upweighting higher quality data, or unintentionally because data deduplication is not perfect and the…

Large language models (LLMs) and classical machine learning methods offer complementary strengths for predictive modeling, yet their fundamentally different representations and training paradigms hinder effective integration: LLMs rely on…

Mathematical reasoning benchmarks are vital for evaluating large language models (LLMs), but many are static and repeatedly exposed through public evaluation and training pipelines, making it difficult to separate genuine reasoning from…

Meta-training, which fine-tunes the language model (LM) on various downstream tasks by maximizing the likelihood of the target label given the task instruction and input instance, has improved the zero-shot task generalization performance.…