pith. sign in

arxiv: 2605.19194 · v1 · pith:RHB7ZHVZnew · submitted 2026-05-18 · 💻 cs.CL

MMoA: An AI-Agent framework with recurrence for Memoried Mixure-of-Agent

Rui Chu This is my paper

Pith reviewed 2026-05-20 10:16 UTC · model grok-4.3

classification 💻 cs.CL
keywords Mixture of AgentsRecurrent MoALSTM gatingMulti-agent LLMsEfficiency optimizationInstruction following benchmarksAdaptive routing
0
0 comments X

The pith

A recurrent LSTM router lets Mixture-of-Agents match standard performance while activating fewer agents for better efficiency.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents MMoA, which adds recurrence via an LSTM-based gating mechanism to the Mixture-of-Agents framework. This allows the router to use both current inputs and historical routing decisions when selecting agents for each aggregation layer. The goal is to make agent selection more context-aware and adaptive. Evaluations across instruction-following benchmarks demonstrate that MMoA delivers win rates close to those of the original MoA while cutting runtime costs through dynamic activation of fewer agents. If correct, this approach could make multi-agent LLM systems more practical for large-scale use by lowering compute demands without sacrificing output quality.

Core claim

By replacing static routers with an LSTM-based recurrence router, MMoA adaptively modulates agent contributions based on current inputs and historical routing decisions. This enables more context-aware aggregation across layers. On standard benchmarks like AlpacaEval 2.0, the system achieves a 58.0% win rate compared to 59.8% for traditional MoA, while improving runtime efficiency by up to 4.6% through reduced agent activations.

What carries the argument

The LSTM-based gating mechanism, which serves as the recurrence router to capture temporal and contextual dependencies for adaptive agent selection.

If this is right

  • MMoA achieves a win rate of 58.0% on AlpacaEval 2.0 versus 59.8% for MoA.
  • Runtime efficiency improves by up to 4.6% by dynamically activating fewer agents.
  • Comparable performance holds on MT-Bench and Arena-Hard benchmarks.
  • The recurrence allows context-aware aggregation without full static routing overhead.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The LSTM memory might help maintain consistency in multi-turn conversations by recalling past agent choices.
  • Extending the recurrence to deeper layers or more agents could further optimize efficiency in larger systems.
  • This dynamic selection strategy may apply to other multi-component AI systems beyond LLMs, such as tool-using agents.

Load-bearing premise

The LSTM-based gating mechanism successfully captures temporal and contextual dependencies across aggregation layers and produces genuinely adaptive agent selection rather than merely adding overhead.

What would settle it

Running MMoA and standard MoA on the same inputs with profiling tools to count active agents per query and measure actual inference time, verifying if efficiency gains exceed the added LSTM computation cost.

Figures

Figures reproduced from arXiv: 2605.19194 by Rui Chu.

Figure 1
Figure 1. Figure 1: Effectiveness of Recurrence Router in MoA [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Blue Line shows the accuracy of MMoA 4.1.1 Performances on Accuracy As shown in [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
read the original abstract

The Mixture-of-Agents (MoA) framework has shown promise in improving large language model (LLM) performance by aggregating outputs from multiple agents. However, existing MoA systems often rely on static routers that do not fully capture temporal and contextual dependencies across aggregation layers. To address this limitation, we propose MMoA, a recurrent MoA architecture that integrates LSTM-based gating into the agent selection process. The recurrence router adaptively modulates agent contributions based on both current inputs and historical routing decisions, enabling more context-aware aggregation. We evaluate MMoA on standard instruction-following benchmarks, including AlpacaEval 2.0, MT-Bench, and Arena-Hard. The results show that MMoA achieves comparable accuracy to traditional MoA while reducing computational overhead by dynamically activating fewer agents. For example, on AlpacaEval 2.0, MMoA achieves a win rate of 58.0%, compared with 59.8% for MoA, while improving runtime efficiency by up to 4.6%. These results suggest that MMoA provides a scalable and efficient approach for adaptive multi-agent LLM systems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper proposes MMoA, a recurrent extension of the Mixture-of-Agents (MoA) framework that integrates an LSTM-based gating mechanism to adaptively select and modulate agent contributions based on current inputs and historical routing decisions. It evaluates the approach on instruction-following benchmarks including AlpacaEval 2.0, MT-Bench, and Arena-Hard, claiming comparable accuracy to static MoA (e.g., 58.0% vs. 59.8% win rate on AlpacaEval 2.0) while achieving up to 4.6% runtime efficiency gains through dynamic activation of fewer agents.

Significance. If the efficiency improvements can be rigorously verified as arising from adaptive agent selection rather than implementation artifacts, MMoA would represent a practical advance for scalable multi-agent LLM systems by addressing limitations of static routers in capturing temporal dependencies. The work builds on existing MoA literature but currently lacks the empirical grounding needed to establish its contribution clearly.

major comments (2)
  1. [Abstract] Abstract: the central efficiency claim (up to 4.6% runtime improvement via fewer activated agents) is load-bearing yet unsupported by any reported statistics on mean or distribution of agents selected per query, wall-clock/FLOPs breakdowns separating LSTM overhead from agent calls, or ablation replacing the recurrent gate with a static router of matched parameter count.
  2. [Abstract] Abstract: benchmark results such as the 58.0% win rate on AlpacaEval 2.0 are presented without error bars, variance estimates, or details on how agent activation counts were measured, rendering the 'comparable accuracy' and efficiency assertions unverifiable from the given text.
minor comments (1)
  1. [Title] Title: contains apparent typographical errors ('Memoried' for 'Memory', 'Mixure' for 'Mixture', and singular 'Agent' instead of 'Agents') that should be corrected for consistency with the abstract and standard terminology.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address each major comment below and will revise the manuscript to provide the requested empirical details and statistical rigor.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central efficiency claim (up to 4.6% runtime improvement via fewer activated agents) is load-bearing yet unsupported by any reported statistics on mean or distribution of agents selected per query, wall-clock/FLOPs breakdowns separating LSTM overhead from agent calls, or ablation replacing the recurrent gate with a static router of matched parameter count.

    Authors: We agree that the efficiency claims require stronger empirical grounding. In the revised manuscript we will report the mean and distribution of the number of agents activated per query under MMoA versus the static baseline. We will also add wall-clock and FLOPs breakdowns that isolate LSTM gating overhead from agent inference costs, and include an ablation that replaces the recurrent gate with a static router of matched parameter count to isolate the contribution of recurrence. revision: yes

  2. Referee: [Abstract] Abstract: benchmark results such as the 58.0% win rate on AlpacaEval 2.0 are presented without error bars, variance estimates, or details on how agent activation counts were measured, rendering the 'comparable accuracy' and efficiency assertions unverifiable from the given text.

    Authors: We acknowledge that the current presentation lacks necessary statistical detail. The revised version will include error bars or standard deviations for all reported win rates (including the 58.0% on AlpacaEval 2.0) and will explicitly describe the measurement protocol for agent activation counts, including how dynamic selection thresholds and per-query counts were computed. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical benchmark results with no self-referential derivations

full rationale

The paper introduces MMoA as an LSTM-augmented variant of Mixture-of-Agents and reports direct experimental outcomes on AlpacaEval 2.0, MT-Bench, and Arena-Hard. The central efficiency claim (58.0% vs 59.8% win rate with up to 4.6% runtime improvement) is presented as a measured result rather than a quantity derived from or defined in terms of itself. No equations, fitted parameters renamed as predictions, uniqueness theorems, or self-citation chains appear in the abstract or described architecture. The derivation chain consists of an architectural proposal followed by external-benchmark evaluation; these results remain independently falsifiable and do not reduce to the inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Central claim rests on the empirical benchmark results and the unstated premise that LSTM gating adds useful temporal context without destabilizing the aggregation process.

pith-pipeline@v0.9.0 · 5725 in / 997 out tokens · 45923 ms · 2026-05-20T10:16:36.534750+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

300 extracted references · 300 canonical work pages · 2 internal anchors

  1. [1]

    Aho and Jeffrey D

    Alfred V. Aho and Jeffrey D. Ullman , title =. 1972

    work page 1972

  2. [2]

    Publications Manual , year = "1983", publisher =

    work page 1983

  3. [3]

    Chandra and Dexter C

    Ashok K. Chandra and Dexter C. Kozen and Larry J. Stockmeyer , year = "1981", title =. doi:10.1145/322234.322243

    work page doi:10.1145/322234.322243 1981

  4. [4]

    Scalable training of

    Andrew, Galen and Gao, Jianfeng , booktitle=. Scalable training of. 2007 , url=

    work page 2007

  5. [5]

    Dan Gusfield , title =. 1997

    work page 1997

  6. [6]

    Tetreault , title =

    Mohammad Sadegh Rasooli and Joel R. Tetreault , title =. Computing Research Repository , volume =. 2015 , url =

    work page 2015

  7. [7]

    A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =

    Ando, Rie Kubota and Zhang, Tong , Issn =. A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =. Journal of Machine Learning Research , Month = dec, Numpages =. 2005 , url=

    work page 2005

  8. [8]

    and Tukey, John W

    Cooley, James W. and Tukey, John W. , journal=. An algorithm for the machine calculation of complex. 1965 , url=

    work page 1965

  9. [9]

    arXiv preprint arXiv:2408.06793 , year=

    Layerwise recurrent router for mixture-of-experts , author=. arXiv preprint arXiv:2408.06793 , year=

    work page arXiv

  10. [10]

    arXiv preprint arXiv:2310.07188 , year=

    Adaptive gating in mixture-of-experts based language models , author=. arXiv preprint arXiv:2310.07188 , year=

    work page arXiv

  11. [11]

    Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

    Outrageously large neural networks: The sparsely-gated mixture-of-experts layer , author=. arXiv preprint arXiv:1701.06538 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  12. [12]

    GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding

    Gshard: Scaling giant models with conditional computation and automatic sharding , author=. arXiv preprint arXiv:2006.16668 , year=

    work page internal anchor Pith review Pith/arXiv arXiv 2006

  13. [13]

    Proceedings of the 3rd Wordplay: When Language Meets Games Workshop (Wordplay 2022). 2022

    work page 2022

  14. [14]

    A Systematic Survey of Text Worlds as Embodied Natural Language Environments

    Jansen, Peter. A Systematic Survey of Text Worlds as Embodied Natural Language Environments. Proceedings of the 3rd Wordplay: When Language Meets Games Workshop (Wordplay 2022). 2022. doi:10.18653/v1/2022.wordplay-1.1

    work page doi:10.18653/v1/2022.wordplay-1.1 2022

  15. [15]

    A Minimal Computational Improviser Based on Oral Thought

    Montfort, Nick and Bartlett Fernandez, Sebastian. A Minimal Computational Improviser Based on Oral Thought. Proceedings of the 3rd Wordplay: When Language Meets Games Workshop (Wordplay 2022). 2022. doi:10.18653/v1/2022.wordplay-1.2

    work page doi:10.18653/v1/2022.wordplay-1.2 2022

  16. [16]

    Craft an Iron Sword: Dynamically Generating Interactive Game Characters by Prompting Large Language Models Tuned on Code

    Volum, Ryan and Rao, Sudha and Xu, Michael and DesGarennes, Gabriel and Brockett, Chris and Van Durme, Benjamin and Deng, Olivia and Malhotra, Akanksha and Dolan, Bill. Craft an Iron Sword: Dynamically Generating Interactive Game Characters by Prompting Large Language Models Tuned on Code. Proceedings of the 3rd Wordplay: When Language Meets Games Worksho...

    work page doi:10.18653/v1/2022.wordplay-1.3 2022

  17. [17]

    A Sequence Modelling Approach to Question Answering in Text-Based Games

    Furman, Gregory and Toledo, Edan and Shock, Jonathan and Buys, Jan. A Sequence Modelling Approach to Question Answering in Text-Based Games. Proceedings of the 3rd Wordplay: When Language Meets Games Workshop (Wordplay 2022). 2022. doi:10.18653/v1/2022.wordplay-1.4

    work page doi:10.18653/v1/2022.wordplay-1.4 2022

  18. [18]

    Automatic Exploration of Textual Environments with Language-Conditioned Autotelic Agents

    Teodorescu, Laetitia and Yuan, Xingdi and C \^o t \'e , Marc-Alexandre and Oudeyer, Pierre-Yves. Automatic Exploration of Textual Environments with Language-Conditioned Autotelic Agents. Proceedings of the 3rd Wordplay: When Language Meets Games Workshop (Wordplay 2022). 2022. doi:10.18653/v1/2022.wordplay-1.5

    work page doi:10.18653/v1/2022.wordplay-1.5 2022

  19. [19]

    Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022

    work page 2022

  20. [20]

    Separating Hate Speech and Offensive Language Classes via Adversarial Debiasing

    Yuan, Shuzhou and Maronikolakis, Antonis and Sch. Separating Hate Speech and Offensive Language Classes via Adversarial Debiasing. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.1

    work page doi:10.18653/v1/2022.woah-1.1 2022

  21. [21]

    Towards Automatic Generation of Messages Countering Online Hate Speech and Microaggressions

    Ashida, Mana and Komachi, Mamoru. Towards Automatic Generation of Messages Countering Online Hate Speech and Microaggressions. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.2

    work page doi:10.18653/v1/2022.woah-1.2 2022

  22. [22]

    G rease V ision: Rewriting the Rules of the Interface

    Datta, Siddhartha and Kollnig, Konrad and Shadbolt, Nigel. G rease V ision: Rewriting the Rules of the Interface. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.3

    work page doi:10.18653/v1/2022.woah-1.3 2022

  23. [23]

    Improving Generalization of Hate Speech Detection Systems to Novel Target Groups via Domain Adaptation

    Ludwig, Florian and Dolos, Klara and Zesch, Torsten and Hobley, Eleanor. Improving Generalization of Hate Speech Detection Systems to Novel Target Groups via Domain Adaptation. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.4

    work page doi:10.18653/v1/2022.woah-1.4 2022

  24. [24]

    `` Zo Grof ! '' : A Comprehensive Corpus for Offensive and Abusive Language in D utch

    Ruitenbeek, Ward and Zwart, Victor and Van Der Noord, Robin and Gnezdilov, Zhenja and Caselli, Tommaso. `` Zo Grof ! '' : A Comprehensive Corpus for Offensive and Abusive Language in D utch. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.5

    work page doi:10.18653/v1/2022.woah-1.5 2022

  25. [25]

    Counter- TWIT : An I talian Corpus for Online Counterspeech in Ecological Contexts

    Goffredo, Pierpaolo and Basile, Valerio and Cepollaro, Bianca and Patti, Viviana. Counter- TWIT : An I talian Corpus for Online Counterspeech in Ecological Contexts. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.6

    work page doi:10.18653/v1/2022.woah-1.6 2022

  26. [26]

    S tereo KG : Data-Driven Knowledge Graph Construction For Cultural Knowledge and Stereotypes

    Deshpande, Awantee and Ruiter, Dana and Mosbach, Marius and Klakow, Dietrich. S tereo KG : Data-Driven Knowledge Graph Construction For Cultural Knowledge and Stereotypes. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.7

    work page doi:10.18653/v1/2022.woah-1.7 2022

  27. [27]

    The subtle language of exclusion: Identifying the Toxic Speech of Trans-exclusionary Radical Feminists

    Lu, Christina and Jurgens, David. The subtle language of exclusion: Identifying the Toxic Speech of Trans-exclusionary Radical Feminists. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.8

    work page doi:10.18653/v1/2022.woah-1.8 2022

  28. [28]

    Lost in Distillation: A Case Study in Toxicity Modeling

    Chvasta, Alyssa and Lees, Alyssa and Sorensen, Jeffrey and Vasserman, Lucy and Goyal, Nitesh. Lost in Distillation: A Case Study in Toxicity Modeling. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.9

    work page doi:10.18653/v1/2022.woah-1.9 2022

  29. [29]

    Cleansing & expanding the HURTLEX (el) with a multidimensional categorization of offensive words

    Stamou, Vivian and Alexiou, Iakovi and Klimi, Antigone and Molou, Eleftheria and Saivanidou, Alexandra and Markantonatou, Stella. Cleansing & expanding the HURTLEX (el) with a multidimensional categorization of offensive words. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.10

    work page doi:10.18653/v1/2022.woah-1.10 2022

  30. [30]

    Free speech or Free Hate Speech? Analyzing the Proliferation of Hate Speech in Parler

    Israeli, Abraham and Tsur, Oren. Free speech or Free Hate Speech? Analyzing the Proliferation of Hate Speech in Parler. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.11

    work page doi:10.18653/v1/2022.woah-1.11 2022

  31. [31]

    Resources for Multilingual Hate Speech Detection

    Arango Monnar, Ayme and Perez, Jorge and Poblete, Barbara and Salda \ n a, Magdalena and Proust, Valentina. Resources for Multilingual Hate Speech Detection. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.12

    work page doi:10.18653/v1/2022.woah-1.12 2022

  32. [32]

    Enriching Abusive Language Detection with Community Context

    Saleem, Haji Mohammad and Kurrek, Jana and Ruths, Derek. Enriching Abusive Language Detection with Community Context. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.13

    work page doi:10.18653/v1/2022.woah-1.13 2022

  33. [33]

    DeTox: A Comprehensive Dataset for G erman Offensive Language and Conversation Analysis

    Demus, Christoph and Pitz, Jonas and Sch. DeTox: A Comprehensive Dataset for G erman Offensive Language and Conversation Analysis. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.14

    work page doi:10.18653/v1/2022.woah-1.14 2022

  34. [34]

    Multilingual H ate C heck: Functional Tests for Multilingual Hate Speech Detection Models

    R. Multilingual H ate C heck: Functional Tests for Multilingual Hate Speech Detection Models. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.15

    work page doi:10.18653/v1/2022.woah-1.15 2022

  35. [35]

    Distributional properties of political dogwhistle representations in S wedish BERT

    Hertzberg, Niclas and Cooper, Robin and Lindgren, Elina and R. Distributional properties of political dogwhistle representations in S wedish BERT. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.16

    work page doi:10.18653/v1/2022.woah-1.16 2022

  36. [36]

    Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions

    Khurana, Urja and Vermeulen, Ivar and Nalisnick, Eric and Van Noorloos, Marloes and Fokkens, Antske. Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.17

    work page doi:10.18653/v1/2022.woah-1.17 2022

  37. [37]

    Accounting for Offensive Speech as a Practice of Resistance

    Diaz, Mark and Amironesei, Razvan and Weidinger, Laura and Gabriel, Iason. Accounting for Offensive Speech as a Practice of Resistance. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.18

    work page doi:10.18653/v1/2022.woah-1.18 2022

  38. [38]

    Towards a Multi-Entity Aspect-Based Sentiment Analysis for Characterizing Directed Social Regard in Online Messaging

    Zheng, Joan and Friedman, Scott and Schmer-galunder, Sonja and Magnusson, Ian and Wheelock, Ruta and Gottlieb, Jeremy and Gomez, Diana and Miller, Christopher. Towards a Multi-Entity Aspect-Based Sentiment Analysis for Characterizing Directed Social Regard in Online Messaging. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:1...

    work page doi:10.18653/v1/2022.woah-1.19 2022

  39. [39]

    Flexible text generation for counterfactual fairness probing

    Fryer, Zee and Axelrod, Vera and Packer, Ben and Beutel, Alex and Chen, Jilin and Webster, Kellie. Flexible text generation for counterfactual fairness probing. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.20

    work page doi:10.18653/v1/2022.woah-1.20 2022

  40. [40]

    Users Hate Blondes: Detecting Sexism in User Comments on Online R omanian News

    Moldovan, Andreea and Cs. Users Hate Blondes: Detecting Sexism in User Comments on Online R omanian News. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.21

    work page doi:10.18653/v1/2022.woah-1.21 2022

  41. [41]

    Targeted Identity Group Prediction in Hate Speech Corpora

    Sachdeva, Pratik and Barreto, Renata and Von Vacano, Claudia and Kennedy, Chris. Targeted Identity Group Prediction in Hate Speech Corpora. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.22

    work page doi:10.18653/v1/2022.woah-1.22 2022

  42. [42]

    Revisiting Queer Minorities in Lexicons

    Ramesh, Krithika and Kumar, Sumeet and Khudabukhsh, Ashiqur. Revisiting Queer Minorities in Lexicons. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.23

    work page doi:10.18653/v1/2022.woah-1.23 2022

  43. [43]

    HATE - ITA : Hate Speech Detection in I talian Social Media Text

    Nozza, Debora and Bianchi, Federico and Attanasio, Giuseppe. HATE - ITA : Hate Speech Detection in I talian Social Media Text. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022. doi:10.18653/v1/2022.woah-1.24

    work page doi:10.18653/v1/2022.woah-1.24 2022

  44. [44]

    Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  45. [45]

    Changes in Tweet Geolocation over Time: A Study with Carmen 2.0

    Zhang, Jingyu and DeLucia, Alexandra and Dredze, Mark. Changes in Tweet Geolocation over Time: A Study with Carmen 2.0. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  46. [46]

    Extracting Mathematical Concepts from Text

    Collard, Jacob and de Paiva, Valeria and Fong, Brendan and Subrahmanian, Eswaran. Extracting Mathematical Concepts from Text. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  47. [47]

    Data-driven Approach to Differentiating between Depression and Dementia from Noisy Speech and Language Data

    Ehghaghi, Malikeh and Rudzicz, Frank and Novikova, Jekaterina. Data-driven Approach to Differentiating between Depression and Dementia from Noisy Speech and Language Data. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  48. [48]

    Cross-Dialect Social Media Dependency Parsing for Social Scientific Entity Attribute Analysis

    Eggleston, Chloe and O ' Connor, Brendan. Cross-Dialect Social Media Dependency Parsing for Social Scientific Entity Attribute Analysis. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  49. [49]

    Impact of Environmental Noise on A lzheimer ' s Disease Detection from Speech: Should You Let a Baby Cry?

    Novikova, Jekaterina. Impact of Environmental Noise on A lzheimer ' s Disease Detection from Speech: Should You Let a Baby Cry?. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  50. [50]

    Exploring Multimodal Features and Fusion Strategies for Analyzing Disaster Tweets

    Pranesh, Raj. Exploring Multimodal Features and Fusion Strategies for Analyzing Disaster Tweets. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  51. [51]

    NTULM : Enriching Social Media Text Representations with Non-Textual Units

    Li, Jinning and Mishra, Shubhanshu and El-Kishky, Ahmed and Mehta, Sneha and Kulkarni, Vivek. NTULM : Enriching Social Media Text Representations with Non-Textual Units. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  52. [52]

    Robust Candidate Generation for Entity Linking on Short Social Media Texts

    Hebert, Liam and Makki, Raheleh and Mishra, Shubhanshu and Saghir, Hamidreza and Kamath, Anusha and Merhav, Yuval. Robust Candidate Generation for Entity Linking on Short Social Media Texts. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  53. [53]

    T rans POS : Transformers for Consolidating Different POS Tagset Datasets

    Li, Alex and Bankole-Hameed, Ilyas and Singh, Ranadeep and Ng, Gabriel and Gupta, Akshat. T rans POS : Transformers for Consolidating Different POS Tagset Datasets. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  54. [54]

    An Effective, Performant Named Entity Recognition System for Noisy Business Telephone Conversation Transcripts

    Fu, Xue-Yong and Chen, Cheng and Laskar, Md Tahmid Rahman and Tn, Shashi Bhushan and Corston-Oliver, Simon. An Effective, Performant Named Entity Recognition System for Noisy Business Telephone Conversation Transcripts. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  55. [55]

    Leveraging Semantic and Sentiment Knowledge for User-Generated Text Sentiment Classification

    Khan, Jawad and Ahmad, Niaz and Alam, Aftab and Lee, Youngmoon. Leveraging Semantic and Sentiment Knowledge for User-Generated Text Sentiment Classification. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  56. [56]

    An Emotional Journey: Detecting Emotion Trajectories in D utch Customer Service Dialogues

    Labat, Sofie and Hadifar, Amir and Demeester, Thomas and Hoste, Veronique. An Emotional Journey: Detecting Emotion Trajectories in D utch Customer Service Dialogues. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  57. [57]

    Supervised and Unsupervised Evaluation of Synthetic Code-Switching

    Orlov, Evgeny and Artemova, Ekaterina. Supervised and Unsupervised Evaluation of Synthetic Code-Switching. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  58. [58]

    A rab G end: Gender Analysis and Inference on A rabic T witter

    Mubarak, Hamdy and Chowdhury, Shammur Absar and Alam, Firoj. A rab G end: Gender Analysis and Inference on A rabic T witter. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  59. [59]

    Automatic Identification of 5 C Vaccine Behaviour on Social Media

    Sampath Kumar, Ajay Hemanth and Shausan, Aminath and Demartini, Gianluca and Rahimi, Afshin. Automatic Identification of 5 C Vaccine Behaviour on Social Media. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  60. [60]

    Automatic Extraction of Structured Mineral Drillhole Results from Unstructured Mining Company Reports

    Dimeski, Adam and Rahimi, Afshin. Automatic Extraction of Structured Mineral Drillhole Results from Unstructured Mining Company Reports. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  61. [61]

    `` Kanglish alli names! '' Named Entity Recognition for K annada- E nglish Code-Mixed Social Media Data

    S, Sumukh and Shrivastava, Manish. `` Kanglish alli names! '' Named Entity Recognition for K annada- E nglish Code-Mixed Social Media Data. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  62. [62]

    Span Extraction Aided Improved Code-mixed Sentiment Classification

    S, Ramaneswaran and Benhur, Sean and Ghosh, Sreyan. Span Extraction Aided Improved Code-mixed Sentiment Classification. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  63. [63]

    A d BERT : An Effective Few Shot Learning Framework for Aligning Tweets to Superbowl Advertisements

    Das, Debarati and Chenchu, Roopana and Abdollahi, Maral and Huh, Jisu and Srivastava, Jaideep. A d BERT : An Effective Few Shot Learning Framework for Aligning Tweets to Superbowl Advertisements. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  64. [64]

    Increasing Robustness for Cross-domain Dialogue Act Classification on Social Media Data

    Vielsted, Marcus and Wallenius, Nikolaj and van der Goot, Rob. Increasing Robustness for Cross-domain Dialogue Act Classification on Social Media Data. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  65. [65]

    Disfluency Detection for V ietnamese

    Dao, Mai Hoang and Truong, Thinh Hung and Nguyen, Dat Quoc. Disfluency Detection for V ietnamese. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  66. [66]

    A multi-level approach for hierarchical Ticket Classification

    Marcuzzo, Matteo and Zangari, Alessandro and Schiavinato, Michele and Giudice, Lorenzo and Gasparetto, Andrea and Albarelli, Andrea. A multi-level approach for hierarchical Ticket Classification. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  67. [67]

    Towards better structured and less noisy Web data: Oscar with Register annotations

    Laippala, Veronika and Salmela, Anna and R. Towards better structured and less noisy Web data: Oscar with Register annotations. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  68. [68]

    True or False? Detecting False Information on Social Media Using Graph Neural Networks

    Rode-Hasinger, Samyo and Kruspe, Anna and Zhu, Xiao Xiang. True or False? Detecting False Information on Social Media Using Graph Neural Networks. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  69. [69]

    Analyzing the Real Vulnerability of Hate Speech Detection Systems against Targeted Intentional Noise

    Aggarwal, Piush and Zesch, Torsten. Analyzing the Real Vulnerability of Hate Speech Detection Systems against Targeted Intentional Noise. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). 2022

    work page 2022

  70. [70]

    Proceedings of the 4th Workshop of Narrative Understanding (WNU2022). 2022

    work page 2022

  71. [71]

    Uncovering Surprising Event Boundaries in Narratives

    Wang, Zhilin and Jafarpour, Anna and Sap, Maarten. Uncovering Surprising Event Boundaries in Narratives. Proceedings of the 4th Workshop of Narrative Understanding (WNU2022). 2022. doi:10.18653/v1/2022.wnu-1.1

    work page doi:10.18653/v1/2022.wnu-1.1 2022

  72. [72]

    Compositional Generalization for Kinship Prediction through Data Augmentation

    Wei, Kangda and Ghosh, Sayan and Srivastava, Shashank. Compositional Generalization for Kinship Prediction through Data Augmentation. Proceedings of the 4th Workshop of Narrative Understanding (WNU2022). 2022. doi:10.18653/v1/2022.wnu-1.2

    work page doi:10.18653/v1/2022.wnu-1.2 2022

  73. [73]

    How to be Helpful on Online Support Forums?

    Wang, Zhilin and Torres, Pablo E. How to be Helpful on Online Support Forums?. Proceedings of the 4th Workshop of Narrative Understanding (WNU2022). 2022. doi:10.18653/v1/2022.wnu-1.3

    work page doi:10.18653/v1/2022.wnu-1.3 2022

  74. [74]

    GPT -2-based Human-in-the-loop Theatre Play Script Generation

    Rosa, Rudolf and Schmidtov \'a , Patr \' cia and Du s ek, Ond r ej and Musil, Tom \'a s and Mare c ek, David and Obaid, Saad and Nov \'a kov \'a , Marie and Voseck \'a , Kl \'a ra and Dole z al, Josef. GPT -2-based Human-in-the-loop Theatre Play Script Generation. Proceedings of the 4th Workshop of Narrative Understanding (WNU2022). 2022. doi:10.18653/v1/...

    work page doi:10.18653/v1/2022.wnu-1.4 2022

  75. [75]

    G is P y: A Tool for Measuring Gist Inference Score in Text

    Hosseini, Pedram and Wolfe, Christopher and Diab, Mona and Broniatowski, David. G is P y: A Tool for Measuring Gist Inference Score in Text. Proceedings of the 4th Workshop of Narrative Understanding (WNU2022). 2022. doi:10.18653/v1/2022.wnu-1.5

    work page doi:10.18653/v1/2022.wnu-1.5 2022

  76. [76]

    Heroes, Villains, and Victims, and GPT -3: Automated Extraction of Character Roles Without Training Data

    Stammbach, Dominik and Antoniak, Maria and Ash, Elliott. Heroes, Villains, and Victims, and GPT -3: Automated Extraction of Character Roles Without Training Data. Proceedings of the 4th Workshop of Narrative Understanding (WNU2022). 2022. doi:10.18653/v1/2022.wnu-1.6

    work page doi:10.18653/v1/2022.wnu-1.6 2022

  77. [77]

    Narrative Detection and Feature Analysis in Online Health Communities

    Ganti, Achyutarama and Wilson, Steven and Ma, Zexin and Zhao, Xinyan and Ma, Rong. Narrative Detection and Feature Analysis in Online Health Communities. Proceedings of the 4th Workshop of Narrative Understanding (WNU2022). 2022. doi:10.18653/v1/2022.wnu-1.7

    work page doi:10.18653/v1/2022.wnu-1.7 2022

  78. [78]

    Looking from the Inside: How Children Render Character ' s Perspectives in Freely Told Fantasy Stories

    van Duijn, Max and van Dijk, Bram and Spruit, Marco. Looking from the Inside: How Children Render Character ' s Perspectives in Freely Told Fantasy Stories. Proceedings of the 4th Workshop of Narrative Understanding (WNU2022). 2022. doi:10.18653/v1/2022.wnu-1.8

    work page doi:10.18653/v1/2022.wnu-1.8 2022

  79. [79]

    Proceedings of the 2nd Workshop on Deriving Insights from User-Generated Text. 2022

    work page 2022

  80. [80]

    Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV Conversion

    Park, Seongmin and Lee, Jihwa. Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV Conversion. Proceedings of the 2nd Workshop on Deriving Insights from User-Generated Text. 2022. doi:10.18653/v1/2022.wit-1.1

    work page doi:10.18653/v1/2022.wit-1.1 2022

Showing first 80 references.