The First Workshop on the Application of LLM Explainability to Reasoning and Planning
COLM 2025, Montreal, Canada
Joined May 2025
- Tweets32
- Following16
- Followers78
- Likes12
XLLM-Reason-Plan retweeted
@DakingRai is one of my best. Highly recommend for any team recruiting for LLM Interp/reasoning/controllability/etc. He plans to graduate in a year or so. Go meet him at the poster session or msg him for a chat directly!
Exhibit Hall C,D,E #3815
Thu 4 Dec 4:30 p.m. PST — 7:30 p.m. PST
This quoted post is unavailable.
XLLM-Reason-Plan retweeted
(1/3) Started this as a side project on a whim and had fun presenting it at the COLM 2025 XLLM-Reason-Plan Workshop recently. @XllmReasonPlan
Built a small dataset of rebus puzzles to see how VLMs reason through visual wordplay.
Dataset: huggingface.co/datasets/pmov…
XLLM-Reason-Plan retweeted
We are very honored to receive the Best Paper Award! Reviewers’s comments are very insightful! We really appreciate such valuable recognition from the workshop committee!
Best Paper Award goes to Li et al., "Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation" @liruizhe94
🎉Our (partial) organizer team (left to right: @YilunZhou @DakingRai @ZiyuYao @hanjie_chen and Abu Saparov). We hope to see everyone in the next iteration soon!
#COLM2025 Finally, the awards!🏆 We announced one Best Paper Award, one Special Recognition Award, and two Honorable Mentions. Congrats to the authors! See 🧵👇
Honorable Mentions go to:
Li et al., "Rethinking Human Preference Evaluation of LLM Rationales", and
Rai et al., "Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones" @DakingRai
Special Recognition Award goes to Shi et al., "When Models Know More Than They Can Explain: Quantifying
Knowledge Transfer in Human-AI Collaboration" @BenShi34
Best Paper Award goes to Li et al., "Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation" @liruizhe94
#COLM2025 Our last invited talk if you are still around: Prof. Zining Zhu is presenting "Improving LLM reasoning with mechanistic insights" @zhuzining
#COLM2025 Dr. Jenn Wortman Vaughan presenting "Challenges in Human-Agent Communication" @jennwvaughan . Happening now!
#COLM2025 Prof. Mark Riedl presenting "Reasoning, Explanation, and Human-Centered AI". @mark_riedl Welcome back to the afternoon session!
XLLM-Reason-Plan retweeted
#COLM2025 Prof. Mark Riedl presenting "Reasoning, Explanation, and Human-Centered AI". @mark_riedl Welcome back to the afternoon session!
#COLM2025 Prof. Ana Marasović talking about Internal Reasoning, Faithfulness, and more! @anmarasovic
XLLM-Reason-Plan retweeted
This will be presenting at The First Workshop on the Application of LLM Explainability to Reasoning and Planning! @XllmReasonPlan
Ever wonder why math reasoning fails without CoT? The bottleneck isn’t “abstraction” but “calculation”. I’ll be presenting at COLM on Friday (11–12) — come chat about reasoning × interpretability!
@Mila_Quebec @RBCBorealis
🔗arxiv.org/pdf/2505.23701
#COLM2025 #EMNLP2025
#COLM2025 Prof. Greg Durrett presenting "LLM Reasoning Beyond Scaling" @gregd_nlp
