Synthetic Contrastive Reasoning for Multi-Table Q&A
This work constructs a synthetic contrastive reasoning-trace dataset for multi-table Q&A, fine-tunes LLMs with Contrastive Preference Optimization, and achieves 9.7%-16.3% absolute average improvements on MMQA, with gains up to 21 percentage points.
[2606.05382] Synthetic Contrastive Reasoning for Multi-Table Q&A
[Submitted on 3 Jun 2026]
Title:Synthetic Contrastive Reasoning for Multi-Table Q&A
View a PDF of the paper titled Synthetic Contrastive Reasoning for Multi-Table Q&A, by Ankit Pratap Singh and 2 other authors
View PDF HTML (experimental)
Abstract:Multi-table question answering requires models to retrieve relevant evidence, link schemas, and perform compositional reasoning across relational tables. Existing multi-table Q&A resources typically provide questions and final answers but lack reasoning supervision that explains how answers are derived. To address this gap, we construct a synthetic contrastive reasoning-trace dataset for MMQA by generating validated positive traces and plausible negative traces with heterogeneous LLMs. We then use the resulting preference pairs to fine-tune open-weight LLMs with Contrastive Preference Optimization (CPO). Across Qwen3-14B, Mistral-8B, and Llama-3.1-8B, CPO achieves absolute average improvements over Q&A supervised fine-tuning ranging from 9.7%-16.3%, with gains up to 21 percentage points on MMQA. Ablations show that heterogeneous positive and negative trace generators strengthen the contrastive signal, and automated as well as human evaluations indicate that the generated pairs are largely faithful, coherent, and meaningfully contrastive.
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.05382 [cs.AI]
(or arXiv:2606.05382v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.05382
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Ankit Pratap Singh [view email] [v1] Wed, 3 Jun 2026 19:35:54 UTC (722 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Synthetic Contrastive Reasoning for Multi-Table Q&A, by Ankit Pratap Singh and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)