XLLM-Reason-Plan @ COLM

11 papers17 directions

Papers by Year

2025 11

Top Research Directions

Research directions most represented by papers from this venue.

Activation Patching for Mechanistic Interpretability 2
Scaling In Context Task Representations to Complex Reasoning 1
How Fine Tuning Reshapes Internal Model Circuitry 1
How Language Models Collapse Linguistic Ambiguity 1
Linear Concept Directions in Latent Spaces 1
Projecting Intermediate Transformer States to the Vocabulary Space 1
Activation Steering for Inference Time Model Control 1
Understanding Depth Saturation in Deep Neural Networks 1
Recurrent Weight Sharing for Parameter Efficient Depth 1
Dynamic Inference Compute Allocation 1
Overcoming the Limits of Multi Step Language Model Reasoning 1
Systematic Biases in Large Language Model Evaluators 1
Schema Linking for Text to SQL Parsing 1
The Cross-Genre Generalization Gap 1
Intermediate Reasoning Chains for Deliberative Inference 1

Top Authors

AuthorPapers
Ranjay Krishna2
Abbas Ghaddar1
Bin Wang1
Damien Graux1
Enqi Liu1
Ge Zhang1
Guangyi Liu1
Helena Vasconcelos1
Himabindu Lakkaraju1
Hongzhe Du1
Idan Shenfeld1
Irina Saparina1
Isha Puri1
Jackie Chi Kit Cheung1
Jacob Andreas1
Jeff Z. Pan1
Jiaming Zhou1
Jianye HAO1
Karim Saraipour1
Kaustubh Vyas1

Impactful Papers

Papers from this venue that shaped research clusters.

Influential

Papers

TitleYear
Are General-Purpose LLMs Ready for Planning? A Large- Scale Evaluation in PDDL2025
Before You 〈think/〉, Monitor: Implementing Flavell's Metacognitive Framework in LLMs2025
Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation2025
Case-Based Reasoning Enhances the Predictive Power of LLMs in Drug-Drug Interaction2025
Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing2025
Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data2025
How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence2025
Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer2025
ReCalibrate: RL for Uncertainty-Aware Reasoning in LLMs2025
Rethinking (Human) Preference Evaluation of LLM Rationales2025
Rethinking Human Preference Evaluation of LLM Rationales2025