Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Textual Aesthetics in Large Language ModelsMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)6 citationsJan 1, 2025Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented GenerationMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)6 citationsJan 1, 2025When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMsCohere · Conference on Empirical Methods in Natural Language Processing (EMNLP)6 citationsJan 1, 2025Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document UnderstandingAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)6 citationsJan 1, 2025Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and PreferencesAllen Institute for AI · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)6 citationsJan 1, 2025LegoSLM: Connecting LLM with Speech Encoder using CTC PosteriorsAlphabet, Google DeepMind · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)6 citationsJan 1, 2025Meaningful Pose-Based Sign Language EvaluationGoogle DeepMind · Conference on Machine Translation (WMT)6 citationsJan 1, 2025Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics DataAlphabet · neural information processing systems6 citationsJan 1, 2025Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language ModelsMicrosoft · neural information processing systems6 citationsJan 1, 2025Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual SparsityNVIDIA · neural information processing systems6 citationsJan 1, 2025Scalable In-context Ranking with Generative ModelsAlphabet, Google DeepMind · neural information processing systems6 citationsJan 1, 2025Pool Me Wisely: On the Effect of Pooling in Transformer-Based ModelsMicrosoft · neural information processing systems6 citationsJan 1, 2025IF-Guide: Influence Function-Guided Detoxification of LLMsAnthropic, Google DeepMind · neural information processing systems6 citationsJan 1, 2025Fast Last-Iterate Convergence of SGD in the Smooth Interpolation RegimeAlphabet · neural information processing systems6 citationsJan 1, 2025Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial ImputationMicrosoft · neural information processing systems6 citationsJan 1, 2025StreamMel: Real-Time Zero-Shot Text-to-Speech Via Interleaved Continuous Autoregressive ModelingMicrosoft · IEEE Signal Processing Letters6 citationsJan 1, 2025A Training-free LLM-based Approach to General Chinese Character Error CorrectionAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting6 citationsJan 1, 2025Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention LearningiFlytek · Proceedings of the conference - Association for Computational Linguistics. Meeting6 citationsJan 1, 2025OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal RetrievalMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting6 citationsJan 1, 2025Do not Abstain! Identify and Solve the UncertaintyAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting6 citationsJan 1, 2025If Eleanor Rigby Had Met ChatGPT: A Study on Loneliness in a Post-LLM WorldMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting6 citationsJan 1, 2025Steering off Course: Reliability Challenges in Steering Language ModelsAllen Institute for AI · Proceedings of the conference - Association for Computational Linguistics. Meeting6 citationsJan 1, 2025From Tools to Teammates: Evaluating LLMs in Multi-Session Coding InteractionsCohere · Proceedings of the conference - Association for Computational Linguistics. Meeting6 citationsJan 1, 2025PodAgent: A Comprehensive Framework for Podcast GenerationMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)6 citationsJan 1, 2025Embedding-Converter: A Unified Framework for Cross-Model Embedding TransformationAlphabet · Proceedings of the conference - Association for Computational Linguistics. Meeting6 citationsJan 1, 2025