Related papers: Grounding Multi-Hop Reasoning in Structural Causal…

Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat…

Despite significant advancements in the general capability of large language models (LLMs), they continue to struggle with consistent and accurate reasoning, especially in complex tasks such as mathematical and code reasoning. One key…

Large Vision-Language Models (LVLMs) have become powerful general-purpose assistants, yet their predictions often lack reliability and interpretability due to insufficient grounding in visual evidence. The emerging thinking-with-images…

The rapid rise of synthetic media has made deepfake detection a critical challenge for online safety and trust. Progress remains constrained by the scarcity of large, high-quality datasets. Although multimodal large language models (LLMs)…

Recent work has proposed multi-hop models and datasets for studying complex natural language reasoning. One notable task requiring multi-hop reasoning is fact checking, where a set of connected evidence pieces leads to the final verdict of…

Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be a highly effective strategy for endowing Large Language Models (LLMs) with robust multi-step reasoning abilities. However, its design and optimizations remain tailored…

Large language models (LLMs) have demonstrated remarkable advances in reasoning capabilities. However, their performance remains constrained by limited access to explicit and structured domain knowledge. Retrieval-Augmented Generation (RAG)…

Recent advances in multi-modal large language models (MLLMs) have significantly improved object-level grounding and region captioning. However, they remain limited in visual relation understanding, struggling even with binary relation…

The Structure Gap between probabilistic LLM generation and deterministic schema requirements hinders automated workflows. We propose RL-Struct, a lightweight framework using Gradient Regularized Policy Optimization (GRPO) with a…

Large Language Models (LLMs) have demonstrated remarkable capabilities in knowledge acquisition, reasoning, and tool use, making them promising candidates for autonomous agent applications. However, training LLM agents for complex…

Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improves accuracy, it can degrade reasoning. We propose a two-stage approach: SFT on disease…

In this study, we introduced a new benchmark consisting of a curated dataset and a defined evaluation process to assess the compositional reasoning capabilities of large language models within the chemistry domain. We designed and validated…

With the rapid advancement of vision-language models, an increasing number of studies have explored their potential for SVG generation tasks. Although existing approaches improve performance by constructing large-scale SVG datasets and…

Factual Error Correction (FEC) aims to revise inaccurate text into statements that are factually consistent with external evidence. Although recent methods perform well on single-hop correction, they often treat claims as atomic units and…

Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly by boosting their mathematical performance. However, GRPO and related entropy-regularization methods…

Large language models (LLMs) perform well on multi-hop reasoning, yet how they internally compose multiple facts remains unclear. Recent work proposes \emph{hop-aligned circuit hypothesis}, suggesting that bridge entities are computed…

Reinforcement learning from human feedback (RLHF) or verifiable rewards (RLVR), the standard paradigm for aligning LLMs or building recent SOTA reasoning models, is highly sensitive to noise from inconsistent or erroneous rewards. Yet, the…

Reinforcement Learning from Human Feedback (RLHF) plays a crucial role in aligning large language models (LLMs) with human values and preferences. However, the quality and stability of the trained reward model largely determine the final…

We introduce an approach to counterfactual inference based on merging information from multiple datasets. We consider a causal reformulation of the statistical marginal problem: given a collection of marginal structural causal models (SCMs)…

Enhancing the reasoning capabilities of language models (LMs) remains a key challenge, especially for tasks that require complex, multi-step decision-making where existing Chain-of-Thought (CoT) approaches struggle with consistency and…