Papers with fine-grained reasoning
ALERT: Adapt Language Models to Reasoning Tasks (2023.acl-long)
Copied to clipboard
Ping Yu, Tianlu Wang, Olga Golovneva, Badr AlKhamissi, Siddharth Verma, Zhijing Jin, Gargi Ghosh, Mona Diab, Asli Celikyilmaz
| Challenge: | Large language models have shown increasing in-context learning capabilities with scaling up the model and data sizes. |
| Approach: | They propose a benchmark and suite of analyses to evaluate reasoning skills of large language models. |
| Outcome: | The proposed model compares pre-trained and fine-tuned models on tasks that require reasoning skills to solve. |
Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graph for Retrieval-Augmented Generation (2026.eacl-long)
Copied to clipboard
| Challenge: | Standard unstructured RAG methods rely on embedding-similarity matching and lack any general mechanism to encode or exploit chronological information. |
| Approach: | They propose a retrieval-augmented generation framework that integrates a document retrieval generator with an exter-nal document retriever to enhance the model's accuracy. |
| Outcome: | The proposed framework outperforms state-of-the-art unstructured and KG-based RAG frameworks on causal and character consistency queries. |
GLAF: Global-to-Local Aggregation and Fission Network for Semantic Level Fact Verification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing fact verification models lack fine-grained reasoning over key entities . GLAF uses local fission reasoning to capture latent logical relations between clues . |
| Approach: | They propose a global-to-local fission and fissional network to capture latent logical relations hidden in multiple evidence clues. |
| Outcome: | The proposed network achieves state-of-the-art on a FEVER dataset with a 77.62% FEVER score. |
SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Multimodal large language models (MLLMs) are a promising tool for document understanding, but they are not able to handle complex multi-page visual documents. |
| Approach: | They propose a flexible agentic framework for understanding multi-modal, multi-page, and multi-layout documents . SlideAgent employs specialized agents and decomposes reasoning into three specialized levels . |
| Outcome: | a new agentic framework improves accuracy over open-source and proprietary models . it decomposes reasoning into three levels to capture themes and visual cues . the framework is based on a multimodal large language model and a MLLM . |
HyperMR: Hyperbolic Hypergraph Multi-hop Reasoning for Knowledge-based Visual Question Answering (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies on knowledge-based visual question answering (KBVQA) describe the semantic distance using the actual Euclidean distance between two nodes, which leads to distortion in modeling knowledge graphs with hierarchical and scale-free structure. |
| Approach: | They propose to use the actual Euclidean distance between two nodes to solve a problem of hierarchical and free-scale knowledge graphs. |
| Outcome: | Extensive experiments on the KVQA, PQ and PQL datasets demonstrate the effectiveness of HyperMR for strong-hierarchy knowledge graphs. |
LILaC: Late Interacting in Layered Component Graph for Open-domain Multimodal Multihop Retrieval (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing multimodal document retrieval frameworks focus on textual, tabular, and visual elements, but there is a shift toward open-domain multimodal retrieval. |
| Approach: | They propose a multimodal retrieval framework that uses a component graph and a late-interaction-based subgraph retrieval method to capture semantic relationships between components. |
| Outcome: | The proposed framework achieves state-of-the-art retrieval performance on all five benchmarks . it is based on a layered component graph representing multimodal information at two layers . |
Dual-Path Counterfactual Integration for Multimodal Aspect-Based Sentiment Classification (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for multimodal aspect-based sentiment classification rely on superficial correlations and spurious cues. |
| Approach: | They propose a Dual-Path Counterfactual Integration framework that explicitly models counterfactual reasoning in multimodal contexts. |
| Outcome: | The proposed framework improves model robustness by explicitly modeling counterfactual reasoning in multimodal contexts. |
Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Cognitive distortions are systematic errors in thinking that occur when individuals perceive and interpret external information, leading to a negative conclusion that does not correspond to reality. |
| Approach: | They propose a framework that combines Large Language Models with a Multiple-Instance Learning architecture to enhance interpretability and expression-level reasoning. |
| Outcome: | The proposed framework improves interpretability and expression-level reasoning on Korean and English datasets. |