Natural Language Processing

This paper presents a fully automated method for PDDL translation and planning using LLMs and environment interaction, achieving a 66% success rate on challenging PDDL domains.

LESS achieves state-of-the-art Referring 3D Segmentation using only binary masks, significantly reducing labeling effort and improving efficiency with a novel single-stage pipeline.

LEDEX: A novel training framework significantly boosts LLMs’ code self-debugging by using automated data collection, supervised fine-tuning, and reinforcement learning, leading to more accurate code a…

Language models excel at generating programs for algorithmic tasks, but struggle with soft reasoning. COGEX leverages pseudo-programs and program emulation to tackle these tasks, while COTACS searches…

RL-instructed language models excel at strategic communication in One Night Ultimate Werewolf, demonstrating the importance of discussion tactics in complex games.

Goal-conditioned contrastive learning boosts language reward model performance and enables better control of language model generation.

CoupleNet dynamically links protein sequences and structures for improved representations, surpassing state-of-the-art methods in function prediction, particularly for uncommon proteins.

Linear transformers efficiently learn sparse contextual bigrams by leveraging both in-context and global information, achieving polynomial sample complexity.

Active learning for video captioning is enhanced by a novel algorithm that prioritizes ’learnability’, diversity, and uncertainty to address annotation inconsistency.

LB-CL: A novel parameter-efficient continual learning method for LLMs that boosts performance and reduces forgetting by leveraging parametric knowledge transfer and maintaining orthogonal low-rank sub…

LCGen: A novel method for view-consistent text-to-3D generation, resolving the ‘Janus Problem’ by strategically using low-certainty priors to align viewpoints and optimize the generation process.

LaPael improves LLM knowledge injection by applying learned noise to early layers, enabling diverse and efficient knowledge updates without repeated external model usage.

LLM-DA dynamically adapts LLM-generated rules for accurate, interpretable temporal knowledge graph reasoning, significantly improving accuracy without fine-tuning.

Teach LLMs uncertainty for reliable high-stakes predictions: Fine-tuning with graded examples significantly improves LLM’s uncertainty calibration and generalizes well.

New conformal inference methods enhance LLM validity by providing adaptive validity guarantees and improving the quality of LLM outputs, addressing prior methods’ limitations.

ECO prompts enable efficient LLM unlearning by corrupting prompts flagged for forgetting, achieving promising results across various LLMs and tasks with minimal side effects.

This paper presents a novel method for large language model (LLM) unlearning, enabling LLMs to ‘forget’ undesirable behaviors by using only negative examples. This computationally efficient approach o…

Large language models (LLMs) achieve lossless gradient compression, surpassing existing methods by up to 17.2%, thereby advancing distributed learning efficiency.

Language models struggle with hierarchical information. This work introduces Hierarchy Transformer Encoders (HITs), a novel method to retrain transformer encoders using hyperbolic geometry and special…

LangGround: MARL agents learn human-interpretable communication via LLM-grounded training, enabling effective human-agent collaboration.