I'm at #EMNLP2025 in Suzhou🇨🇳 to present these papers in the coming days:

Nov 7, Session 14, 12:30-13:30 @ Hall C – Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems (Wang et al.) @qiaw99.bsky.social

🗞️ aclanthology.org/2025.finding...

Our synthesis reveals a growing demand for more rigorous, causal evaluation. By outlining the state of the art and identifying key challenges, this survey provides a roadmap for future research toward making models more transparent.

This survey has been accepted at @blackboxnlp.bsky.social at EMNLP

We consider concept descriptions in open-vocabulary settings, the evolving landscape of automated and human metrics for evaluating them, and the datasets that underpin this research.

This is a companion paper to our PRISM paper that was accepted at NeurIPS last week: bsky.app/profile/lkop...

🔍 Are you curious about uncovering the underlying mechanisms and identifying the roles of model components (neurons, …) and abstractions (SAEs, …)?

We provide the first survey of concept description generation and evaluation methods.

Joint effort w/ @lkopf.bsky.social

📄 arxiv.org/abs/2510.01048

📍 Venue: Vietnam Institute for Advanced Study in Mathematics, Hanoi, Vietnam — during INLG 2025.

💡 If you'll be in the region for INLG or EMNLP 2025, this is a great opportunity to connect and share your work!

📅 Submission deadline: August 26, 2025

Excited to announce the first-ever Workshop for Young Researchers in Natural Language Generation (YNLG), supported by @siggen.bsky.social, taking place on October 29, 2025 in Hanoi, Vietnam, co-located with INLG 2025.
Call for Submissions is out now!

ynlg-workshop.github.io

We introduce the TableEval benchmark and investigate the effectiveness and robustness of text-based and multimodal LLMs on table understanding through a cross-domain & cross-modality evaluation.

Joint work by DFKI SLT incl. Fabio Barth, Raia Abu Ahmad, @malteos.bsky.social @pjox.bsky.social

Our contribution to the FEVER shared task: Our EFC framework stays competitive against this year's baseline while significantly reducing the average runtime per claim achieved through semantic filtering strategies for veracity prediction.

Joint work by the XplaiNLP group incl. @jingyng.bsky.social

We investigate how rationale generation is affected by readability level control, and find that explanations are adaptable, but the observed distinction between readability levels does not fully match the desired complexity.

Joint work with @hakimov.bsky.social.

Using saliency scores, label flip verification and few-shot prompting, our FitCF method outperforms three state-of-the-art baselines on counterfactual example generation.

Joint work with @simost.bsky.social, Luis Felipe Villa-Arenas, Sebastian Möller, Vera Schmitt.

Code: github.com/qiaw99/FitCF

Glad to announce our #FAccT2025 paper about gender bias in feature attribution methods, led by Mahdi Dhaini, will be presented tomorrow in 🇬🇷 Athens as part of the "Evaluating Explainable AI" session from 10:45 AM to 12:15 PM in Amphitheatre Ioannis Despotopoulos: programs.sigchi.org/facct/2025/p...

Successfully defended my PhD yesterday! 🎓 🎉
Special thanks to my mentor Sebastian Möller and professors Sina Zarrieß @clausebielefeld.bsky.social, Christin Seifert, and @matthiasboehm7.bsky.social for being part of my committee.
Will continue working on XAI & NLP as a post-doc at TU Berlin & BIFOLD

We evaluate Cross-Refine on three datasets incl. a bilingual dataset (English/German) and find that it outperforms the SOTA approach with smaller-sized LLMs, and that it can generate explanations in the target language more consistently.

GitHub: github.com/qiaw99/Cross...

Our new COLING 2025-accepted work Cross-Refine, led by @qiaw99.bsky.social, approaches the problem of free-text rationalization with a generator-critic setup: The generator outputs initial explanations and the critic provides the feedback for them. #COLING2025

arXiv: arxiv.org/abs/2409.07123

We conduct an evaluation of several LLMs on CoXQL using different parsing strategies. Our parsing approach with template validations (MP+) surpasses the performance of previous approaches. We also discover that intents with multiple slots remain highly challenging for LLMs.

We contribute to conversational explainable artificial intelligence (ConvXAI) systems based on large language models (LLMs) by filling the gap of training data and covering a broad range of XAI methods to map user requests onto.

Accepted at #EMNLP2024: CoXQL, an NLP dataset for user intent recognition in Conversational XAI. Qianli Wang will present his work in Miami later today at 4:00PM local time in Poster Session C (Riverfront Hall).
ACL Anthology: aclanthology.org/2024.finding...
GitHub: github.com/DFKI-NLP/CoXQL