Papers with aggregation
Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for federated fine-tuning for Large Language Models suffer from performance degradation at low ranks in heterogeneous data settings. |
| Approach: | They propose a low-rank adaptive model with Alternating freeze and Adaptive rank selection which reduces the number of uploaded parameters by 99.8% . |
| Outcome: | The proposed low-rank Adaptation maintains robustness even under extreme heterogeneity and low rank conditions while preserving communication efficiency. |
LinkTransformer: A Unified Package for Record Linkage with Transformer Language Models (2024.acl-demos)
Copied to clipboard
| Challenge: | Large language models (LLMs) are used for many computational analyses, but approximate string matching packages are not widely used in social science applications. |
| Approach: | The open-source package LinkTransformer provides an end-to-end software for performing record linkage and other data cleaning tasks with transformer LLMs. |
| Outcome: | The open-source package LinkTransformer outperforms standard methods in a variety of languages and settings. |
Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large Language Models exhibit a progressive left-leaning bias, but can also produce behavior that aligns with socioeconomic groups. |
| Approach: | They analyze whether persona prompting can accurately predict individual voting decisions . they find that they can simulate the voting behavior of European Parliament members reasonably well . |
| Outcome: | The proposed model can predict the voting behavior of European Parliament members reasonably well, with a weighted F1 score of approximately 0.793. |
REQUAL-LM: Reliability and Equity through Aggregation in Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | a new method for finding reliable and equitable LLM outputs is developed . REQUAL-LM does not require specialized hardware and does not impose a significant computing load . |
| Approach: | They propose a method for finding reliable and equitable LLM outputs through aggregation. |
| Outcome: | The proposed method minimizes harmful bias while finding reliable outputs . it does not require specialized hardware and does not impose a significant computing load . |
Hybrid Graphs for Table-and-Text based Question Answering using LLMs (2025.naacl-long)
Copied to clipboard
| Challenge: | Current methods for QA rely on fine-tuning and high-quality data, which is difficult to obtain. |
| Approach: | They propose a Hybrid Graph-based approach for Table-Text QA that leverages Large Language Models without fine-tuning. |
| Outcome: | The proposed approach improves Exact Match scores by 10% on Hybrid-QA and 5.4% on OTT-QA. |
k-Rater Reliability: The Correct Unit of Reliability for Aggregated Human Annotations (2022.acl-short)
Copied to clipboard
| Challenge: | aggregation has been a common strategy for dealing with unreliable data since the inception of crowdsourcing . however, many applications that rely on aggregate ratings only report the reliability of individual ratings, which is the incorrect unit of analysis. |
| Approach: | They propose to use k-rater reliability (kRR) to determine the correct data reliability for crowdsourced datasets. |
| Outcome: | The proposed method produces similar results on WordSim-353 datasets. |
Towards Reliable Agents: Benchmarking Customized LLM-Based Retrieval-Augmented Generation Frameworks with Deployment Validation (2025.naacl-industry)
Copied to clipboard
| Challenge: | Existing benchmarks for general-purpose RAG systems, such as CRAG, RGB, MultiHop-RAG, and CRUD-RAGG, are limited and lack a benchmark specifically tailored to evaluate frameworks. |
| Approach: | They evaluated OpenAI’s Assistants API versus a RAG assistant built with Langchain and deployed a system based on benchmark insights as a course assistant over a two-year span. |
| Outcome: | The proposed benchmarks show that domain-specific retrieval impacts response accuracy and highlight key challenges in real-world deployment. |
Crowdsourcing and Aggregating Nested Markable Annotations (P19-1)
Copied to clipboard
| Challenge: | Existing methods for identifying markables for coreference annotation are task and language-independent and can be used for a variety of other annotation tasks. |
| Approach: | They propose a method for identifying markables for coreference annotation that combines automatic markable detectors with checking with a Game-With-A-Purpose (GWAP) and aggregation using a Bayesian annotation model. |
| Outcome: | The proposed method improves mention boundaries on news and other genres by over seven percentage points compared with state-of-the-art, domain-independent automatic mention detectors and almost three points over an in-domain mention detector. |
Mitigating Degree Bias in Hypergraphs via Attribute-as-Structure Approach (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing “attribute-as-feature” approaches do not create new aggregation pathways for sparsely connected entities. |
| Approach: | They propose an “attribute-as-structure” approach specifically designed for heterogeneous hypergraphs that integrates attributes directly into the hypergraph topology as distinct node types. |
| Outcome: | The proposed approach integrates attributes directly into the hypergraph topology as distinct node types, creating new structural pathways to enrich sparsely connected entities while preserving semantic distinctiveness within complex complex interactions. |
OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference (N19-1)
Copied to clipboard
| Challenge: | Existing methods for knowledge extraction and alignment are limited in quality and performance. |
| Approach: | They propose to integrate OpenIE extractions in the form of (subject, predicate, object) triples with Knowledge Bases (KB) |
| Outcome: | The proposed method improves state-of-the-art for OpenIE extractions and boosts performance on OpenIE from semi-structured data. |
Detecting Speaker Personas from Conversational Texts (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on personas are pre-defined and hard to obtain before a conversation . a new task aims to detect speaker persona based on conversational text . |
| Approach: | They propose a task to detect speaker personas based on conversational text . they build a dataset for SPD and propose utterance-to-profile matching networks . |
| Outcome: | The proposed task outperforms baseline models and utterance-to-profile (U2P) matching networks. |
Exploring End-to-End Differentiable Natural Logic Modeling (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to integrate natural logic with neural networks are brittle and prone to fail in the presence of noise and uncertainty. |
| Approach: | They propose to integrate natural logic with neural networks to create differentiable models that integrate natural reasoning with subsymbolic vector representations and neural components. |
| Outcome: | The proposed model can model monotonicity-based reasoning, compared to baseline models without inductive bias. |
MGIMN: Multi-Grained Interactive Matching Network for Few-shot Text Classification (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for text classification fail to generalize to unseen classes with very few labeled text instances per class. |
| Approach: | They propose a meta-learning method which performs instance-wise comparison followed by aggregation to generate class-wise matching vectors instead of prototype learning. |
| Outcome: | Experiments show that the proposed method outperforms existing methods under both the standard and generalized FSL settings. |
RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research on retrieval-augmented language models has two main problems: determining what information to retrieve and effectively combining retrieved information during generation. |
| Approach: | They propose a retrieval-augmented language model that captures current and future information from source and target text into a latent space. |
| Outcome: | The proposed model is more efficient than explicit raw text, but limited by context length and noise. |
An Analysis of Annotated Corpora for Emotion Classification in Text (C18-1)
Copied to clipboard
| Challenge: | Several datasets have been annotated and published for classification of emotions. |
| Approach: | They aggregated emotion corpora in a common file format with a shared annotation schema . they perform cross-corpus classification experiments to gain insight and a better understanding of differences . |
| Outcome: | The proposed model can be trained on a subset of corpora, but not on all corporata. |
Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News Recommendation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing news recommendation methods rely on centralized storage of user click behavior data, which may lead to privacy concerns and hazards. |
| Approach: | They propose a federated learning framework for privacy-preserving news recommendation . they propose aggregation of news representations and user model by a client . |
| Outcome: | The proposed framework reduces computation and communication cost on clients while keeping promising model performance. |
Database reasoning over text (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models cannot handle database queries such as “List/Count all female athletes who were born in 20th century”. |
| Approach: | They propose a modular architecture to answer database-style queries over multiple spans from text and aggregate them at scale. |
| Outcome: | The proposed architecture scales to databases containing thousands of facts whereas current models are limited by how many facts can be encoded. |
Neural Pipeline for Zero-Shot Data-to-Text Generation (2022.acl-long)
Copied to clipboard
| Challenge: | In data-to-text generation, training on in-domain data leads to overfitting and repeating training data noise. |
| Approach: | They propose to train pretrained language models on general-domain text-based operations by transforming single-item descriptions with modules trained on ordering, aggregation, and paragraph compression. |
| Outcome: | The proposed approach enables D2T generation from RDF triples in zero-shot settings. |
Aggregation Artifacts in Subjective Tasks Collapse Large Language Models’ Posteriors (2025.naacl-long)
Copied to clipboard
| Challenge: | In-context Learning (ICL) is the primary method for performing natural language tasks with Large Language Models. |
| Approach: | They examine whether aggregation is a confounding factor in the modeling of subjective tasks . they find it is possible for minority annotators to better align with LLMs . |
| Outcome: | The proposed method is based on aggregation of annotations in a dataset with appropriate priors. |
Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval over haystacks (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing multilingual long-context benchmarks are myopic and inherently limited, as successful recall alone does not indicate a model’s capacity to reason over extended contexts. |
| Approach: | They propose a new synthetic benchmark for multilingual long-context reasoning that includes bAbI-style tasks that test multi-hop inference, aggregation, and epistemic reasoning. |
| Outcome: | The proposed benchmarks are based on a multilingual long-context model and span seven languages. |
Convex Aggregation for Opinion Summarization (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in text autoencoders have significantly improved the quality of the latent space, allowing models to generate consistent text from aggregated latent vectors. |
| Approach: | They develop a framework which searches input-output word overlap for latent vector aggregation. |
| Outcome: | The proposed framework improves the quality of the latent space and establishes state-of-the-art performance on two opinion summarization benchmarks. |
OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work has advanced agent selection and result aggregation, efficient linguistic interactions for deep collaboration among expert agents remain a critical bottleneck. |
| Approach: | They propose a knowledge-aware adaptive collaboration framework to enhance cognitive synergy in multi-agent systems with large language models. |
| Outcome: | The proposed framework improves synergy between agents and language models by enabling agents to dynamically perceive their collaborators’ cognitive states. |
Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing multi-document QA benchmarks require information from only a few documents with limited cross-document reasoning. |
| Approach: | They propose a benchmark for multi-document analytical QA that extracts and synthesizes information across multiple documents to perform quantitative analysis. |
| Outcome: | The proposed approach improves both process and outcome metrics but still has bottlenecks compared to human experts. |
If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering (2021.naacl-main)
Copied to clipboard
| Challenge: | et al. : evidence retrieval is highly dependent on partial, incorrect or no supporting knowledge. |
| Approach: | They propose a method that retrieves and reranks evidence facts jointly . they propose to account for links between sentences and coverage with the given query . |
| Outcome: | The proposed approach achieves state-of-the-art evidence retrieval performance on two multi-hop question answering datasets. |
Debate, Deliberate, Decide (D3): A Cost-Aware Adversarial Framework for Reliable and Interpretable LLM Evaluation (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing evaluation tools for Large Language Models (LLMs) are inconsistency, bias, and lack of transparent decision criteria. |
| Approach: | They propose a cost-aware, adversarial multi-agent framework that orchestrates structured debate among role-specialized agents to produce reliable and interpretable evaluations. |
| Outcome: | The proposed framework orchestrates structured debate among role-specialized agents to produce reliable and interpretable evaluations. |
A Framework for Shared Agreement of Language Tags beyond ISO 639 (2020.lrec-1)
Copied to clipboard
| Challenge: | Identification and annotation of languages in an unambiguous and standardized way is essential for the description of linguistic data. |
| Approach: | They propose a pattern that extends the BCP 47 sub-tag ‘privateuse’ and is able to overcome the limits of BCP47 and ISO 639. |
| Outcome: | The proposed pattern overcomes the limitations of BCP 47 and ISO 639 for the identification of lesser-known languages, endangered languages, regional varieties or historical stages of a language. |
Attributable and Scalable Opinion Summarization (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for opinion summarization encode sentences from customer reviews into a hierarchical discrete latent space. |
| Approach: | They propose a method that encodes customer reviews into a hierarchical discrete latent space and then identifies common opinions based on their frequency. |
| Outcome: | The proposed method generates summaries that are more informative than previous work and more grounded in the input reviews. |
Hierarchical Aggregation of Dialectal Data for Arabic Dialect Identification (2022.lrec-1)
Copied to clipboard
| Challenge: | Previous work on Arabic Dialect identification focused on specific dialect levels and labels . since dialectal differences tend to be more subtle relative terms to language differences, the DID task is harder than language identification. |
| Approach: | They propose to define a standard hierarchical schema for Arabic Dialect identification . they map 29 different data sets to this schema and use it to aggregate the data . |
| Outcome: | The proposed schemas and methods are extensible to other languages and dialect groups. |
Additive manifesto decomposition: A policy domain aware method for understanding party positioning (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for estimating policy domain aware party similarity are limited to global domains. |
| Approach: | They propose a workflow for estimating policy domain aware party similarity by aggregating policy domains into a single figure . they use a set of tools to extract party positions on major policy axes via multidimensional scaling. |
| Outcome: | The proposed method yields high correlation when predicting party similarity at a global level and provides accurate party-specific positions even with automatically labelled policy domains. |
Open-WikiTable : Dataset for Open Domain Question Answering with Complex Reasoning over Table (2023.findings-acl)
Copied to clipboard
| Challenge: | Open-WikiTable is the first open domain question answering dataset that requires complex reasoning over tables. |
| Approach: | They propose to use open-domain question answering over tables to extract questions from tables. |
| Outcome: | The dataset is publicly available. it is built upon WikiSQL and WikiTableQuestions. |
LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network (2020.acl-main)
Copied to clipboard
Wanjun Zhong, Duyu Tang, Zhangyin Feng, Nan Duan, Ming Zhou, Ming Gong, Linjun Shou, Daxin Jiang, Jiahai Wang, Jian Yin
| Challenge: | Existing methods for fact checking textual statements are not yet available. |
| Approach: | They propose a neural network approach capable of leveraging logical operations for fact checking . they use a textual statement and semi-structured tables to generate a program from it . |
| Outcome: | The proposed approach achieves state-of-the-art performance on TABFACT dataset . it derives a program (a.k.a. logical form) of the statement in semantic parsing manner . |
Prompting with Phonemes: Enhancing LLMs’ Multilinguality for Non-Latin Script Languages (2025.naacl-long)
Copied to clipboard
Hoang H Nguyen, Khyati Mahajan, Vikas Yadav, Julian Salazar, Philip S. Yu, Masoud Hashemi, Rishabh Maheshwary
| Challenge: | Multilingual LLMs have achieved remarkable benchmark performance, but continue to underperform on non-Latin script languages. |
| Approach: | They propose to integrate phonemic transcriptions as complementary signals to induce script-invariant representations by integrating phonemic and orthographic transcriptions. |
| Outcome: | The proposed approach improves performance for Latin and non-Latin script languages, with 12.6% performance improvement and 15.1% performance improvement compared to randomized ICL retrieval. |
A Herd of Language Models Makes a Better Zero-shot Annotator for Clinical Named Entity Recognition (2026.findings-acl)
Copied to clipboard
| Challenge: | Clinical named entity recognition (NER) is a core task in clinical NLP. |
| Approach: | They propose a label-modeling method for M**ulti-LLM **A**nnotation using **R**epresentation learning to capture contextual similarity. |
| Outcome: | The proposed method improves the average F1 score by 8.6% over zero-shot baselines while reducing annotation costs. |
A Gated Self-attention Memory Network for Answer Selection (D19-1)
Copied to clipboard
| Challenge: | Existing deep learning approaches for answer selection use word-level comparison followed by aggregation. |
| Approach: | They propose a new gated self-attention memory network for answer selection task . they combine a transfer learning technique from a large-scale online corpus to create a gated network . |
| Outcome: | The proposed model outperforms existing methods on two standard answer selection datasets: TrecQA and WikiQA. |
Multi-hop Reading Comprehension through Question Decomposition and Rescoring (P19-1)
Copied to clipboard
| Challenge: | Existing systems for multi-hop reading comprehension decompose compositional questions into simpler sub-questions . authors propose a system that learns to break compositional multi- hop questions into simple singlehop sub-question . |
| Approach: | They propose a system that decomposes a compositional question into simpler sub-questions . they propose recast subquestion generation as a span prediction problem . |
| Outcome: | The proposed system generates as effective as human-authored sub-questions using 400 examples . it also provides explainable evidence for its decision making in the form of sub-questions . |
Charge-Based Prison Term Prediction with Deep Gating Network (D19-1)
Copied to clipboard
| Challenge: | Existing work merely predicts the total prison term, but in reality a defendant is often charged with multiple crimes. |
| Approach: | They propose a charge-based prison term prediction task that better fits real needs and makes it more accurate and interpretable. |
| Outcome: | The proposed method achieves state-of-the-art performance for charge-specific feature selection and aggregation. |
Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches treat tool use as a problem of prompt design, API documents specification, or supervised or unsupervised alignment. |
| Approach: | They propose a knowledge-augmented tool execution framework that integrates experiential knowledge with reasoning-width-expanded inference and knowledge-aware training. |
| Outcome: | The proposed framework improves on BFCL-V3 and AppWorld on three model scales. |
SkillAggregation: Reference-free LLM-Dependent Aggregation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods in NLP assign equal weight to all LLM judgments or are designed for specific tasks such as hallucination detection. |
| Approach: | They propose a method that learns to combine LLM judgments without additional data or ground truth to exploit the judge estimates during inference. |
| Outcome: | The proposed method outperforms Crowdlayer on all tasks and yields the best performance over all approaches on the majority of tasks. |
Multilingual Federated Low-Rank Adaptation for Collaborative Content Anomaly Detection across Multilingual Social Media Participants (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent developments in multilingual social media platforms (SNS) exacerbate new challenges in SNS content anomaly detection due to data islands and linguistic imbalance. |
| Approach: | They propose a multilingual Federated LoRA based on SVD-based language-specific disentanglement of LoRA blocks and a local orthogonal tuning strategy to detect content anomalies. |
| Outcome: | The proposed solution is superior in multilingual content anomaly detection while reducing multilingual knowledge conflicts and communication rounds. |
A Picture is Worth a Thousand Words? An Empirical Study of Aggregation Strategies for Visual Financial Document Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | Visual RAG is an alternative to traditional RAG, but it requires hundreds of patch tokens per document to retrieve and store information. |
| Approach: | They propose to aggregate documents into a single vector to avoid semantic loss . they find global texture dominance is the root cause of this loss - they say . |
| Outcome: | The proposed model shows that aggregation obscures semantic changes in financial documents . global texture dominance is the root cause, and the model scales are consistent across models and embeddings. |
Self-Para-Consistency: Improving Reasoning Tasks at Low Cost for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that self-consistency decoding can improve performance for complex reasoning tasks with large language models. |
| Approach: | They propose a self-consistency decoding strategy that generates multiple paraphrases for each test question and then generates reasoning paths for the original and all the paraphrased questions based on greedy decoding. |
| Outcome: | The proposed strategy reduces the sampling number and improves performance on complex reasoning tasks. |
Human-LLM Hybrid Text Answer Aggregation for Crowd Annotations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on crowd text answer aggregation focus on individual crowd workers' average performance, but the role of LLMs as aggregators is not well-studied. |
| Approach: | They propose a human-LLM hybrid text answer aggregation method with a Creator-Aggregator Multi-Stage crowdsourcing framework. |
| Outcome: | The proposed method is based on a Creator-Aggregator Multi-Stage crowdsourcing framework. |
ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show ToM outperforms existing divide-and-conquer frameworks . RAG relies on similarity-based rankings to retrieve and reason over chunks based on logical coherence . |
| Approach: | They propose a Tree-oriented MapReduce framework for long-context reasoning . it leverages the hierarchical structure of long documents by constructing a DocTree . |
| Outcome: | Experimental results show that ToM outperforms existing divide-and-conquer frameworks and RAGs . the proposed framework improves logical coherence and long-context reasoning on 70B+ LLMs compared to existing approaches . |
How Robust Are Large Language Models for Clinical Numeracy? An Empirical Study on Numerical Reasoning Abilities in Clinical Contexts (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluations of Large Language Models for clinical numerical reasoning provide limited operation-level coverage and limited robustness of numerical understanding across clinical note formats. |
| Approach: | They propose a benchmarking tool that evaluates four main types of clinical numeracy . they present longitudinal MIMIC-IV vital-sign records in three semantically equivalent representations . |
| Outcome: | The proposed benchmark evaluates four main types of clinical numeracy: value retrieval, arithmetic computation, relational comparison, and aggregation. |
Interactive Semantic Parsing with Reinforcement Learning for Knowledge Graph Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to improve LLM reliability rely on factual hallucinations . Existing methods rely only on graph traversal, resulting in imprecise retrieval and heavy post-processing burdens. |
| Approach: | They propose a framework that integrates knowledge Graphs as structured, high-fidelity buffers to enhance LLM reliability. |
| Outcome: | The proposed framework allows logical constraints to be dynamically interleaved with graph search while optimizing via reinforcement learning with only final answer feedback eliminates the need for gold program annotations. |
Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) training with Mixture-of-Experts policies remains fragile and prone to reward collapse. |
| Approach: | They propose a router shift-based policy optimization method that computes a per-token router-shift ratio conditioned on the previously activated experts and applies stop-gradient and a lower-bound floor. |
| Outcome: | The proposed method achieves better performance and greater stability than previous methods. |
MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MEXA is a training-free framework that performs modality- and task-aware aggregation of multiple expert models to enable effective multimodal reasoning across diverse domains. |
| Approach: | MEXA is a training-free framework that performs modality- and task-aware aggregation of multiple expert models. |
| Outcome: | MEXA performs modality- and task-aware aggregation of multiple expert models . it generates interpretable textual reasoning outputs and reasons over them using a Large Reasoning Model (LRM) MEX A consistently delivers performance improvements over strong multimodal benchmarks . |
SILO-BENCH: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems (2026.acl-long)
Copied to clipboard
Yuzhe Zhang, Feiran Liu, Yi Shan, Xinyi Huang, Xin Yang, Yueqi Zhu, Xuxin Cheng, Cao Liu, Ke Zeng, Terry Jingchen Zhang, Wenyuan Jiang
| Challenge: | Existing benchmarks conflate coordination ability with role-based priors. |
| Approach: | They propose a role-free benchmark for evaluating free-form collaboration under information silos. |
| Outcome: | The proposed benchmark systematically probes coordination capabilities under information silos using 54 configurations and 3 frontier LLMs. |
The Best of Both Worlds: Combining Parallel and Sequential Inference Scaling via Aggregation Fine-Tuning (2026.findings-acl)
Copied to clipboard
| Challenge: | Empirical results show that AFT-trained models achieve substantial gains with test-time scaling. |
| Approach: | They introduce a supervised fine-tuning paradigm where models synthesize multiple draft responses into a single, refined answer. |
| Outcome: | Empirical results show that AFT-trained models outperform baseline models while eliminating external guidance. |
MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Excessive refinement can cause over-correction and reduce performance, authors say . they say MAgICoRe is a framework for multi-agent iteration for coarse-to-fine refinement . |
| Approach: | They propose a framework for multi-agent iteration for coarse-to-fine refinement that reduces excessive refinement by categorizing problems as easy or hard. |
| Outcome: | The proposed framework beats Self-Consistency by 3.4%, Best-of-k by 3.2%, and Self-Refine by 4.0% on Llama-3-8B and GPT- 3.5. |
Global Adaptive Momentum Meets Local Personalized Perturbation: Efficient Federated LLM Fine-Tuning with Zeroth-Order Gradients (2026.acl-long)
Copied to clipboard
| Challenge: | federated fine-tuning of large language models provides privacy-preserving approach to deploying pervasive generative AI services. |
| Approach: | They propose a federated framework for fine-tuning large language models . they propose unified optimization and local personalized perturbation for ZO gradients . |
| Outcome: | The proposed framework outperforms existing methods for integrating ZO gradients in federated learning over diverse heterogeneous data settings. |
Parallel Test-Time Scaling for Latent Reasoning Models (2026.acl-long)
Copied to clipboard
| Challenge: | Parallel test-time scaling is a pivotal approach for enhancing large language models. |
| Approach: | They propose two uncertainty-inspired stochastic strategies for parallel test-time scaling for latent reasoning models and a Latent Reward Model for aggregation. |
| Outcome: | The proposed model scales well with compute and enables effective trajectory selection. |