Pith. sign in

REVIEW 5 cited by

Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.17822 v1 pith:VHQZ3VTH submitted 2024-05-28 cs.CL cs.AI

classification cs.CLcs.AI
keywords conversationalconv-coaquestionaccuracyactionsansweringchain-of-actioncomparisons
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present a Conversational Chain-of-Action (Conv-CoA) framework for Open-domain Conversational Question Answering (OCQA). Compared with literature, Conv-CoA addresses three major challenges: (i) unfaithful hallucination that is inconsistent with real-time or domain facts, (ii) weak reasoning performance in conversational scenarios, and (iii) unsatisfying performance in conversational information retrieval. Our key contribution is a dynamic reasoning-retrieval mechanism that extracts the intent of the question and decomposes it into a reasoning chain to be solved via systematic prompting, pre-designed actions, updating the Contextual Knowledge Set (CKS), and a novel Hopfield-based retriever. Methodologically, we propose a resource-efficiency Hopfield retriever to enhance the efficiency and accuracy of conversational information retrieval within our actions. Additionally, we propose a conversational-multi-reference faith score (Conv-MRFS) to verify and resolve conflicts between retrieved knowledge and answers in conversations. Empirically, we conduct comparisons between our framework and 23 state-of-the-art methods across five different research directions and two public benchmarks. These comparisons demonstrate that our Conv-CoA outperforms other methods in both the accuracy and efficiency dimensions.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety

    cs.AI 2025-08 conditional novelty 6.0 of 10

    Evo-MARL jointly trains all task agents with GRPO and an evolutionary attack pool, lowering jailbreak success rates by up to 21 points and modestly raising task accuracy.

  2. Extending LLM Context via Associative Recurrent Memory

    cs.CL 2026-07 conditional novelty 5.0 of 10

    ARMT-augmented 1B-class LLMs, trained with continued pretraining, synthetic long data, curriculum, and selective memory layers, keep in-window quality while generalizing past 32k–65k tokens at constant memory and ~30%...

  3. FairReason: Balancing Reasoning and Social Bias in MLLMs

    cs.AI 2025-07 conditional novelty 5.0 of 10

    A 1:4 debias-to-reasoning training mix under GRPO reinforcement learning yields the best bias-reasoning trade-off in small MLLMs, cutting measured stereotype scores by about 10% while retaining about 88% of reasoning ...

  4. UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations

    cs.CL 2025-07 reject novelty 5.0 of 10

    A single LLM jointly fine-tuned for conversational dense retrieval and retrieval-augmented generation beats separate retriever-plus-generator pipelines on most test collections, though its headline benchmark was conta...

  5. A Survey of the State-of-the-Art in Conversational Question Answering Systems

    cs.CL 2025-09 conditional novelty 2.0 of 10

    A review that categorizes ConvQA components, techniques, models, and datasets, with no new experimental result.

Pith tools