Related papers: A Logically Consistent Chain-of-Thought Approach f…

Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchronized with the computation that determines the answer. We…

Chain-of-Thought (CoT) is a technique that guides Large Language Models (LLMs) to decompose complex tasks into multi-step reasoning through intermediate steps in natural language form. Briefly, CoT enables LLMs to think step by step.…

Large Language Models (LLMs) have recently achieved impressive results in complex reasoning tasks through Chain of Thought (CoT) prompting. However, most existing CoT methods rely on using the same prompts, whether manually designed or…

Stance detection on social media aims to identify attitudes expressed in tweets towards specific targets. Current studies prioritize Large Language Models (LLMs) over Small Language Models (SLMs) due to the overwhelming performance…

Stance detection, the classification of attitudes expressed in a text towards a specific topic, is vital for applications like fake news detection and opinion mining. However, the scarcity of labeled data remains a challenge for this task.…

LLMs can perform multi-step reasoning through Chain-of-Thought (CoT), but they cannot reliably verify their own logic. Even when they reach correct answers, the underlying reasoning may be flawed, undermining trust in high-stakes scenarios.…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically…

Stance detection, which aims to identify public opinion towards specific targets using social media data, is an important yet challenging task. With the proliferation of diverse multimodal social media content including text, and images…

Implicit Chain-of-Thought (CoT) methods offer a token-efficient alternative to explicit CoT reasoning in Large Language Models (LLMs), but a persistent performance gap has limited their adoption. We identify a core latent instability issue…

Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images by integrating information from a composed query (reference image and modification text) without training samples. Existing methods primarily combine caption models…

Compositional Zero-Shot Learning (CZSL) aims to recognize novel attribute-object compositions based on the knowledge learned from seen ones. Existing methods suffer from performance degradation caused by the distribution shift of label…

Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive traces. Existing latent reasoning methods offer a promising…

Zero-shot in-context learning (ZS-ICL) aims to conduct in-context learning (ICL) without using human-annotated demonstrations. Most ZS-ICL methods use large language models (LLMs) to generate (input, label) pairs as pseudo-demonstrations…

Compositional Zero-shot Learning (CZSL) aims to recognize novel concepts composed of known knowledge without training samples. Standard CZSL either identifies visual primitives or enhances unseen composed entities, and as a result,…

While Large Language Models (LLMs) have recently shown impressive results in reasoning tasks, their application to pedestrian trajectory prediction remains challenging due to two key limitations: insufficient use of visual information and…

Chain-of-Thought (CoT) reasoning has emerged as a key technique for eliciting complex reasoning in Large Language Models (LLMs). Although interpretable, its dependence on natural language limits the model's expressive bandwidth. Continuous…

This paper describes our submission to the MEDIQA-CORR 2024 shared task for automatically detecting and correcting medical errors in clinical notes. We report results for three methods of few-shot In-Context Learning (ICL) augmented with…

Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can parse natural queries about the visual content and generate human-like outputs. In this work, we explore the ability of these models to…

Object detection has achieved a huge breakthrough with deep neural networks and massive annotated data. However, current detection methods cannot be directly transferred to the scenario where the annotated data is scarce due to the severe…

Chain-of-thought (CoT) reasoning has exhibited impressive performance in language models for solving complex tasks and answering questions. However, many real-world questions require multi-modal information, such as text and images.…