Related papers: Diagnosing Knowledge Conflict in Multimodal Long-C…
We present chain-of-knowledge (CoK), a novel framework that augments large language models (LLMs) by dynamically incorporating grounding information from heterogeneous sources. It results in more factual rationales and reduced hallucination…
Large Language Models have been shown to contain extensive world knowledge in their parameters, enabling impressive performance on many knowledge intensive tasks. However, when deployed in novel settings, LLMs often encounter situations…
Recent multimodal large language models (MLLMs) have demonstrated significant potential in open-ended conversation, generating more accurate and personalized responses. However, their abilities to memorize, recall, and reason in sustained…
While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…
From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response signifies safe reasoning throughout the entire process.…
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…
Retrieval Augmented Generation (RAG) is a commonly used approach for enhancing large language models (LLMs) with relevant and up-to-date information. However, the retrieved sources can often contain conflicting information and it remains…
Recent advancements in multimodal large language models (MLLMs) have demonstrated exceptional performance in multimodal perception and understanding. However, leading open-source MLLMs exhibit significant limitations in complex and…
Vision language models (VLM) demonstrate sophisticated multimodal reasoning yet are prone to hallucination when confronted with knowledge conflicts, impeding their deployment in information-sensitive contexts. While existing research…
Large Language Models (LLMs) excel at generating natural language answers, yet their outputs often remain unverifiable and difficult to trace. Knowledge Graphs (KGs) offer a complementary strength by representing entities and their…
A common approach for teaching large language models (LLMs) to reason is to train on chain-of-thought (CoT) traces of in-distribution reasoning problems, but such annotated data is costly to obtain for every problem of interest. We want…
Large Language Models (LLMs) face significant accuracy degradation due to insufficient reasoning ability when dealing with complex and abstract tasks. Thought structures such as Chain of Thought (CoT) and Tree of Thought (ToT) focus on…
Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning tasks, yet they often struggle with problems involving missing information, exhibiting issues such as incomplete responses, factual errors, and…
Large Language Models (LLMs) employing Chain-of-Thought (CoT) prompting have broadened the scope for improving multi-step reasoning capabilities. We generally divide multi-step reasoning into two phases: path generation to generate the…
Large Language Models (LLMs) have demonstrated strong performance across a wide range of tasks, yet they still struggle with complex mathematical reasoning, a challenge fundamentally rooted in deep structural dependencies. To address this…
Multimodal large language models (MLLMs) have demonstrated strong capabilities on vision-and-language tasks. However, recent findings reveal an imbalance in their reasoning capabilities across visual and textual modalities. Specifically,…
Large language models (LLMs) are increasingly used in domains where causal reasoning matters, yet it remains unclear whether their judgments reflect normative causal computation, human-like shortcuts, or brittle pattern matching. We…
Large language models (LLMs) encode parametric knowledge about world facts and have shown remarkable performance in knowledge-driven NLP tasks. However, their reliance on parametric knowledge may cause them to overlook contextual cues,…
Large Language Models (LLMs) trained via Reinforcement Learning (RL) have recently achieved impressive results on reasoning benchmarks. Yet, growing evidence shows that these models often generate longer but ineffective chains of thought…
Despite great progress, existing multimodal large language models (MLLMs) are prone to visual hallucination, greatly impeding their trustworthy applications. In this paper, we study this problem from the perspective of visual-spatial…