Papers for

legal document teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Collaborative agents improve automated related work writing in research

Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation

Abstract: Automatic Related Work Generation (RWG) significantly reduces the human time and effort required to author the Related Work Section (RWS) of a research paper. However, prior methods leveraging multi-agent Large Language Models (LLMs) typically rely on a predefined workflow, where each agent is responsible for a specific step in the entire process. This rigid, static inter-agent coordination limits the adaptive collaboration required to synthesize complex scientific literature. To address this limitation, we propose CREW (Collaborative Reinforcement Learning for Related Work Generation), a novel framework where LLM agents bypass heuristic pipelines to dynamically coordinate by autonomously selecting actions, such as Retrieve, Disseminate, Compose, and Critique, driven by a policy optimized via Independent Proximal Policy Optimization (IPPO). Extensive experiments on a standard RWG benchmark demonstrate that our approach yields substantial quality improvements over strong existing baselines, while significantly reducing token costs. Code is available at https://github.com/YenPBao/CREW-Collaborative-MARL.git

Mon 14 SeptMachine Learning
The gist
Writing the related work section of a research paper takes a lot of time. The authors created a new system called CREW that uses multiple AI agents working together more flexibly to write this section. Instead of following a fixed step-by-step plan, the AI agents choose what actions to take, like finding papers or writing summaries, based on what works best. This approach leads to better writing quality and uses fewer computing resources.
Open → 2609.15721v1

Measuring citation accuracy tradeoffs in compressed retrieval generation

The Attribution-Compression Frontier in Retrieval-Augmented Generation

Abstract: Context compression reduces generator input in retrieval-augmented generation, but answer quality alone does not characterize citation attribution. We measure citation attribution across compression methods and budgets, comparing reranking, extractive selection, abstractive summarization, token pruning, and an extract-cluster-rewrite construction on ASQA and QASPER under a fixed generator and primary entailment evaluator. On ASQA at a nominal 0.25 budget (achieved compression 0.08), a RECOMP-style compressor's citations score 0.86 precision against its summaries but 0.12 against source spans under our re-attributability protocol. These estimates depend on a shared NLI model for span recovery and citation scoring and lack independent human calibration. Extractive selection's observed grounded precision ranges from 0.43 to 0.49 across nominal budgets from one-half to one-tenth of the ASQA context, while answer quality declines. For the same RECOMP setting, claim verification after source recovery yields an unsupported rate of 0.88 versus 0.17 when checking summaries. This gap persists beyond structural rejection of missing provenance, but remains evaluator-dependent. A 200-question TRUE T5-XXL audit also finds emitted--grounded gaps under both fixed and recomputed source mappings, without establishing human-calibrated support rates.

Sun 13 SeptComputation and LanguageArtificial Intelligence
The gist
When computers generate answers using retrieved text, they often need to shorten or compress this text to fit into memory or speed up processing. This paper studies how different ways of shortening the text affect not only the quality of answers but also how accurately the computer can cite the sources of the information. The authors find that some compression methods keep answer quality but lose citation accuracy, meaning the system is less trustworthy about where information came from. They also point out that evaluation depends a lot on the tools used and that more human verification is needed.
Open → 2609.14245v1