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
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.
Forward citations
Cited by 5 Pith papers
-
Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety
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.
-
Extending LLM Context via Associative Recurrent Memory
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%...
-
FairReason: Balancing Reasoning and Social Bias in MLLMs
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 ...
-
UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations
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...
-
A Survey of the State-of-the-Art in Conversational Question Answering Systems
A review that categorizes ConvQA components, techniques, models, and datasets, with no new experimental result.
Discussion (0). Sign in to comment.