mlsanityData to 14 Oct 2026

DS@GT ARC at Touch'e: Large Language Models for Retrieval-Augmented Debate

arXiv 2608.08143 ↗First posted 8 Aug 2026cs.IR cs.CLcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

We extend the DS@GT ARC working-note submission to the Touch'e 2025 Retrieval-Augmented Debate task. The task has two subtasks: generating the next utterance in a simulated debate, and evaluating debate responses according to the Gricean maxims of Quantity, Quality, Relation, and Manner. The DS@GT ARC submission consisted of six leading LLMs from three providers through a retrieval-augmented prompting pipeline. We summarize the results from the working paper and explore whether multi-LLM evaluator agreement is a reliable proxy for official evaluation performance. The analysis shows that frontier LLM systems are strong response generators, and as evaluators they agree strongly within model families. However this consensus does not reliably track the official evaluation target, with the largest gap on the Quality maxim. The accompanying source code for this paper is located at https://github.com/dsgt-arc/touche-2025-rad and https://github.com/dsgt-arc/touche-2025-rad-analysis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 8 of its 12 references that are in the map. First posted on arXiv 8 Aug 2026.

Builds on

8 of 12 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025DS@GT at Touch'e: Large Language Models for Retrieval-Augmented Debate12 Jul

Other references · 7

  1. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 266
  2. 2024Jasper and Stella: distillation of SOTA embedding modelscited by 112
  3. 2020Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methodscited by 98
  4. 2025Shrinking the Generation-Verification Gap with Weak Verifierscited by 24
  5. 2024An Empirical Analysis on Large Language Models in Debate Evaluationcited by 20
  6. 2021Learning From Revisions: Quality Assessment of Claims in Argumentation at Scalecited by 14
  7. 2023The Effect of Scaling, Retrieval Augmentation and Form on the Factual Consistency of Language Modelscited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues
  2. 2025R-Debater: Retrieval-Augmented Debate Generation through Argumentative Memory
  3. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
  4. 2025LLM-Specific Utility for Retrieval-Augmented Generation
  5. 2025MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems
  6. 2024GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering
  7. 2024Are Large Language Models Good at Utility Judgments?
  8. 2024DebateQA: Evaluating Question Answering on Debatable Knowledge