Cognitive Computation Group

Elior Sulem, Siyi Liu (@liusiyi64198), Fengze Liu, Haoyu Wang (@Haoyu_Wang_97), Yu Feng (@AnnieFeng6), Zheng Qi, Yanzhen Shen, Sihao Chen (@soshsihao), Chaitanya Malaviya (@cmalaviya11), Rohit Khoja, Vivek Gupta (@keviv9), Dan Roth (@DanRothNLP), & coauthors!

Congratulations to the authors of our papers at #EMNLP2025 and #SEM2025 in Suzhou! Summaries and links (and remaining *SEM poster session) on our blog: ccgblog.seas.upenn.edu/2025/11/ccg-pa…

📷 New #EMNLP2025 Findings survey paper! “Conflicts in Texts: Data, Implications, and Challenges” Paper: aclanthology.org/2025.findings-… Conflicts are everywhere in NLP — news articles reflecting different perspectives or opposing views, annotators who disagree, LLMs that hallucinate or contradict themselves, and personal/enterprise document collections that grow apart and are conflicting. Most research tackles these in isolation, and our survey provides the first unified view of conflicting information in NLP. We chart the path toward conflict-aware, reliable NLP systems. Builds on our earlier work on: - Multi-perspective dataset aclanthology.org/2021.naacl-mai… and search aclanthology.org/2022.findings-… - Hallucination detection aclanthology.org/2025.findings-… - Open-domain QA with conflicting contexts aclanthology.org/2025.findings-…

Check out our papers at #ICML2025 in Vancouver! Summaries, links, and poster sessions on our blog: ccgblog.seas.upenn.edu/2025/07/ccg-pa…. Congrats to @XingyuFu2, @DanRothNLP, and their co-authors!

I will be in #ICML2025 next week and present #ReFocus on Tuesday afternoon. 📍 West Exhibition Hall B2-B3 #W-202 ⏱️ Tue 15 Jul 4:30 p.m. PDT - 7 p.m. PDT Happy to chat and connect! Feel free to DM 😁 ReFocus link: huggingface.co/datasets/ReFoc…

Pleased to share our #NAACL2025 papers in Albuquerque! We’ve updated our blog post with the various session times – come check them out! ccgblog.seas.upenn.edu/2025/03/ccg-pa… @soshsihao, @cmalaviya11, @liusiyi64198, @Wado_Will, @keviv9, @DanRothNLP

Excited to share our papers at #ICLR2025 in Singapore! Check out the summaries on our blog (ccgblog.seas.upenn.edu/2025/04/ccg-pa…), and then check out the papers at oral session 1B (BIRD) and poster session 2 (for all three)! @AnnieFeng6, @XingyuFu2, @BenZhou96, @muhao_chen, @DanRothNLP

#ICLR2025 Oral LLMs often struggle with reliable and consistent decisions under uncertainty 😵‍💫 — largely because they can't reliably estimate the probability of each choice. We propose BIRD 🐦, a framework that significantly enhances LLM decision making under uncertainty. BIRD = LLM strengths + sound probability theory BIRD leverages LLMs for world modeling and constructs a Bayesian network using LLM-generated variables, enabling interpretable and trustworthy probability estimates. ✨ BIRD using LLaMA-3.1-70B achieves 30% more accurate probability estimates than GPT-4. 📄 Paper: openreview.net/pdf?id=fAAaT82… 💻 Code: github.com/CogComp/BIRD Shoutout to my amazing collaborators: @BenZhou96 @wdwlin @DanRothNLP 🗓️ Oral Session 1B: Thu 24 April, 10:54 a.m. – 11:06 a.m. SGT ➡️ Poster: Thu 24 April, 3:00 p.m. – 5:30 p.m. SGT #AI #LLM #decisionmaking #ProbabilisticAI (1/n)

We’re excited to share our #NAACL2025 conference and findings papers on our blog: ccgblog.seas.upenn.edu/2025/03/ccg-pa…! Congratulations to @soshsihao @cmalaviya11 @liusiyi64198 @Wado_Will @keviv9 @DanRothNLP and their co-authors! (image Mukhopadhyay et al., 2025)

New interview with @muhao_chen, former CCG postdoc, who talks with us about cats and hamsters, LLM safety, and far-flung national parks! ccgblog.seas.upenn.edu/2025/01/interv…

Grateful for Professor Bill Labov and for all his detailed and far-reaching work in the field of sociolinguistics.

Excited to share ✨ Contextualized Evaluations ✨! Benchmarks like Chatbot Arena contain underspecified queries, which can lead to arbitrary eval judgments. What happens if we provide evaluators with context (e.g who's the user, what's their intent) when judging LM outputs? 🧵↓

Before launching into our new semester, we asked our six summer interns to tell us about their experiences working with us this summer. Take a look! Special thanks to @keviv9 and @soshsihao for their excellent mentoring! ccgblog.seas.upenn.edu/2024/08/summer…

With special congratulations to @peterbailechen, @Wado_Will, and @DanRothNLP for their Outstanding Paper Award at the #ACL2024 Workshop on Knowledgeable LMs! "Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval" Peter Baile Chen, Yi Zhang, Dan Roth

Congrats to Peter Baile Chen, Yi Zhang, @DanRothNLP for the Outstanding Paper Award at #ACL2024 Workshop on Knowledgeable LMs! Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval Peter Baile Chen, Yi Zhang, Dan Roth arxiv.org/pdf/2404.09889

We’re excited to share our #ACL2024 conference and findings papers in our newest blog post: ccgblog.seas.upenn.edu/2024/08/ccg-pa…. Check out these papers from today’s sessions and next week’s virtual Findings presentations! Congrats to @keviv9 @Wado_Will @DanRothNLP and their co-authors!

I can’t make it to #ACL2024 in person this year, but I’ll be there virtually! 🎉💻 Thrilled to present our three papers on Complex Data Reasoning—Visual Flowcharts QA, Chart Fact-Checking, and Robustness in Finance QA. 🚀📊📚🔍 Stay tuned for details! @cogcomp @upennnlp @SCAI_ASU

New on the blog: An interview with former CCG student researcher Celine Lee, who talks with us about code, creativity, and making connections in the NLP community! ccgblog.seas.upenn.edu/2024/06/interv…

Excited to share new work done @GoogleDeepMind: 🏔️ DOLOMITES: Domain-Specific Long-Form Methodical Tasks, a new long-form generation benchmark for evaluating language models on **realistic** domain-specific tasks. Website: dolomites-benchmark.github.io Paper: arxiv.org/abs/2405.05938

New on our blog: we’re excited to share our #NAACL2024 papers! ccgblog.seas.upenn.edu/2024/05/naacl-… Congratulations to @soshsihao, @Xiaodong_Yu_126, @cmalaviya11, @BenZhou96, @hangfeng_he, @hongming110, @DanRothNLP, @XingyuFu2, @muhao_chen, @yatskar, and co-authors! (image Yu et al., 2024)