Unstructured Evidence Attribution for Long Context Query Focused Summarization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing systems struggle to copy and properly cite unstructured evidence, which also tends to be “lost-in-the-middle”. |
| Approach: | They propose to extract unstructured evidence spans to improve the trustworthiness of large language models by citing unstructure . they propose to use this dataset as a training supervision for unstructure-based evidence summarization. |
| Outcome: | The proposed pipeline generates more relevant and factually consistent evidence than baselines with no fine-tuning and fixed granularity evidence. |
Similar Papers
Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have raised concerns about reliability and trustworthiness of the models. |
| Approach: | They analyze 134 papers and introduce a taxonomy of evidence-based text generation with LLMs. |
| Outcome: | The proposed methods highlight open challenges and outline promising directions for future work. |
Semantic Span Annotation: An Exploratory Study of LLM Annotation (2026.acl-srw)
Copied to clipboard
| Challenge: | Structured span extraction research is siloed by context length, annotation task, and domain . Identifying a span within a natural language text and affixing it with a semantic label has been considered a core task in NLP . |
| Approach: | They propose a framework for structured span annotation that integrates five datasets under a common JSONL format with character-level offsets. |
| Outcome: | The proposed framework can generalize across four domains under three prompting configurations. |
StructSum: Summarization via Structured Representations (2021.eacl-main)
Copied to clipboard
Vidhisha Balachandran, Artidoro Pagnoni, Jay Yoon Lee, Dheeraj Rajagopal, Jaime Carbonell, Yulia Tsvetkov
| Challenge: | Abstractive summarization models overfit to training corpora, lack of transparency and layout bias . authors propose incorporating latent and explicit dependencies across sentences in source document . |
| Approach: | They propose a framework based on document-level structure induction to address layout bias and lack of transparency in abstractive summarization models. |
| Outcome: | The proposed framework improves coverage of content in the source documents and generates more abstractive summaries by generating more novel n-grams. |
Enhancing Incremental Summarization with Structured Representations (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models struggle with processing extensive input contexts, leading to redundancy or incoherency. |
| Approach: | They propose a chain-of-key update based on JSON structured memory representations to improve summarization performance by 40% and 14% on two public datasets. |
| Outcome: | The proposed method improves summarization performance by 40% and 14% on two datasets. |
Low-Perplexity LLM-Generated Sequences and Where To Find Them (2025.acl-srw)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly applied across various domains, but the ways they leverage their training data during inference remains only partially understood. |
| Approach: | They propose a systematic approach that analyzes low-perplexity sequences and traces them back to their sources in the training data. |
| Outcome: | The proposed pipeline extracts low-perplexity sequences across diverse topics while avoiding degeneration, then trace them back to their sources in the training data. |
Inducing Document Structure for Aspect-based Summarization (P19-1)
Copied to clipboard
| Challenge: | Abstractive summarization systems treat documents as unstructured and generate a single generic summary per document. |
| Approach: | They propose to incorporate document structure into automatic summarization systems . they induce latent document structure and abstractive summarizing objective . |
| Outcome: | The proposed model improves on topic-agnostic baselines and can produce abstractive and extractive aspect-based summaries. |
UniSumEval: Towards Unified, Fine-grained, Multi-dimensional Summarization Evaluation for LLMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks for summarization quality evaluation lack diverse input scenarios, focus on narrowly defined dimensions, and struggle with subjective and coarse-grained annotation schemes. |
| Approach: | They propose to use AI to help human annotations and identifie potentially hallucinogenic input texts. |
| Outcome: | The proposed benchmarks improve on existing benchmarks in terms of input diversity, granularity of human annotations, and evaluation dimensions. |
Logic Haystacks: Probing LLMs’ Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding) (2026.eacl-short)
Copied to clipboard
| Challenge: | Recent large language models claim long context windows, but evaluations often involve simple retrieval tasks or synthetic tasks padded with irrelevant text. |
| Approach: | They use grammars to generate simplified English with logical representations to create long input text while controlling its semantics. |
| Outcome: | The proposed model performs better with realistic distractors than with standard models. |
Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to argument summarization rely on single-pass generation, offering limited support for factual correction or structural refinement. |
| Approach: | They propose a large language diffusion framework that iteratively improves argument summarization by sufficiency-guided remasking and regeneration. |
| Outcome: | Empirical results show that Arg-LLaDA surpasses state-of-the-art baselines in 7 out of 10 evaluation metrics. |
Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Long document question answering requires locating relevant paragraphs within a document to answer a question. |
| Approach: | They propose to exploit the discourse structure commonly found in documents to create a condensed representation of the document, enabling a more comprehensive understanding and analysis of relationships between different parts. |
| Outcome: | The proposed approach retains 99.6% of the best zero-shot approach's performance while processing only 26% of tokens used by the best approach in the information seeking evidence retrieval setup. |