相关论文: Using Contrastive Learning to Improve Two-Way Reas…

Large language models (LLMs) have exhibited remarkable reasoning and planning capabilities. Most prior work in this area has used LLMs to reason through steps from an initial to a goal state or criterion, thereby effectively reasoning in a…

Post-training has demonstrated its importance in enhancing the reasoning capabilities of large language models (LLMs). The primary post-training methods can be categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning…

Large Language Models such as GPTs (Generative Pre-trained Transformers) exhibit remarkable capabilities across a broad spectrum of applications. Nevertheless, due to their intrinsic complexity, these models present substantial challenges…

As machine learning models evolve, maintaining transparency demands more human-centric explainable AI techniques. Counterfactual explanations, with roots in human reasoning, identify the minimal input changes needed to obtain a given output…

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…

Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition. However, limited study has been done on large language models' capability to perform conceptual reasoning. In…

Recently the emergence of novel presentation attacks has drawn increasing attention to face anti-spoofing. However, existing methods tend to memorize data patterns from the training set, resulting in poor generalization to unknown attack…

Fine-tuning large pre-trained language models for downstream tasks remains a critical challenge in natural language processing. This paper presents an empirical analysis comparing two efficient fine-tuning methods - BitFit and adapter…

Instruction Fine-Tuning (IFT) significantly enhances the zero-shot capabilities of pretrained Large Language Models (LLMs). While coding data is known to boost LLM reasoning abilities during pretraining, its role in activating internal…

Reinforcement finetuning (RFT) has emerged as a powerful paradigm for unlocking reasoning capabilities in large language models. However, we identify a critical trade-off: while unconstrained RFT achieves strong reasoning performance, it…

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…

A common challenge towards the adaptability of Large Language Models (LLMs) is their ability to learn new languages over time without hampering the model's performance on languages in which the model is already proficient (usually English).…

Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT…

Enhancing the complex reasoning capabilities of Large Language Models (LLMs) attracts widespread attention. While reinforcement learning (RL) has shown superior performance for improving complex reasoning, its impact on cross-lingual…

Prior work on language model pre-training has explored different architectures and learning objectives, but differences in data, hyperparameters and evaluation make a principled comparison difficult. In this work, we focus on…

Large-scale neural language models exhibit remarkable performance in in-context learning: the ability to learn and reason about the input context on the fly. This work studies in-context counterfactual reasoning in language models, that is,…

In-context Learning (ICL) utilizes structured demonstration-query inputs to induce few-shot learning on Language Models (LMs), which are not originally pre-trained on ICL-style data. To bridge the gap between ICL and pre-training, some…

Current deep learning models are not designed to simultaneously address three fundamental questions: predict class labels to solve a given classification task (the "What?"), simulate changes in the situation to evaluate how this impacts…

We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory. It aims to simulate two ways of thinking in the brain to answer questions,…

The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…