Related papers: Soft Self-Consistency Improves Language Model Agen…
Scaling the amount of compute used to train language models has dramatically improved their capabilities. However, when it comes to inference, we often limit models to making only one attempt at a problem. Here, we explore inference compute…
Self-consistency improves reasoning by aggregating diverse stochastic samples, yet the dynamics behind its efficacy remain underexplored. We reframe self-consistency as a dynamic distributional alignment problem, revealing that decoding…
With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented data depends heavily on…
Large language models (LLMs) have been widely used for problem-solving tasks. Most recent work improves their performance through supervised fine-tuning (SFT) with labeled data or reinforcement learning (RL) from task feedback. In this…
When pretrained language models (LMs) are applied to discriminative tasks such as multiple-choice questions, they place probability mass on vocabulary tokens that aren't among the given answer choices. Spreading probability mass across…
Large language models (LLMs) have shown potential as general evaluators along with the evident benefits of speed and cost. While their correlation against human annotators has been widely studied, consistency as evaluators is still…
Test-time scaling improves large language models' (LLMs) performance by allocating more compute budget during inference. To achieve this, existing methods often require intricate modifications to prompting and sampling strategies. In this…
The rise of Large Language Models (LLMs) has boosted the use of Few-Shot Learning (FSL) methods in natural language processing, achieving acceptable performance even when working with limited training data. The goal of FSL is to effectively…
Large Language Models (LLMs) are increasingly used for automated unit test generation. However, it remains unclear whether these tests reflect genuine reasoning about program behavior or simply reproduce superficial patterns learned during…
While Large language models (LLMs) have proved able to address some complex reasoning tasks, we also know that they are highly sensitive to input variation, which can lead to different solution paths and final answers. Answer consistency…
Self-improvement, where models improve beyond their current performance without external supervision, remains a challenge. The core difficulty is sourcing a training signal stronger than what the model itself can currently produce. Majority…
Large Language Models (LLMs) are increasingly used to simulate human users in interactive settings such as therapy, education, and social role-play. While these simulations enable scalable training and evaluation of AI agents, off-the-shelf…
While Large Language Models (LLMs) excel in language-based agentic tasks, their applicability to unseen, nonlinguistic environments (e.g., symbolic or spatial tasks) remains limited. Previous work attributes this performance gap to the…
Large language models have shown their ability to become effective few-shot learners with prompting, revolutionizing the paradigm of learning with data scarcity. However, this approach largely depends on the quality of prompt…
As large language models (LLMs) often generate plausible but incorrect content, error detection has become increasingly critical to ensure truthfulness. However, existing detection methods often overlook a critical problem we term as…
Prompt engineering is a new paradigm for enhancing the performance of trained neural network models. For optimizing text-style prompts, existing methods usually individually operate small portions of a text step by step, which either breaks…
Multi-agent debate (MAD) is an emerging approach to improving the reasoning capabilities of large language models (LLMs). Existing MAD methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is…
Large language models (LLMs) effectively generate fluent text when the target output follows natural language patterns. However, structured prediction tasks confine the output format to a limited ontology, causing even very large models to…
Large language models (LLMs) achieve strong average performance yet remain unreliable at the instance level, with frequent hallucinations, brittle failures, and poorly calibrated confidence. We study reliability through the lens of…
The learning objective plays a fundamental role to build a recommender system. Most methods routinely adopt either pointwise or pairwise loss to train the model parameters, while rarely pay attention to softmax loss due to its computational…