43 citations · 60 across the 18 of their papers we have counts for
20 papers
Register Tokens for Bounded-State Reasoning in Diffusion Language Models
Albert Ge, Chandan Singh, Yufan Zhuang +3
Masked diffusion language models (dLLMs) generate text by iteratively denoising masked tokens with bidirectional attention. Extending reasoning across generation chunks normally re…
Data-Efficient Adaptation of LLMs via Attention Head Reweighting
Tuomas Oikarinen, Zixiao Chen, Charlotte Siska +3
Learning effectively from limited data is critical in domains like security where labeled examples are scarce. Large language models (LLMs) have demonstrated some capabilities for…
Test-time Recursive Thinking: Self-Improvement without External Feedback
Yufan Zhuang, Chandan Singh, Liyuan Liu +5
Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whe…
Training Language Models to Generate Quality Code with Program Analysis Feedback
Feng Yao, Zilong Wang, Liyuan Liu +7
Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e.g.,…
Text Generation Beyond Discrete Token Sampling
Yufan Zhuang, Liyuan Liu, Chandan Singh +2
In standard autoregressive generation, an LLM predicts the next-token distribution, samples a discrete token, and then discards the distribution, passing only the sampled token as…
Interpretable Next-token Prediction via the Generalized Induction Head
Eunji Kim, Sriya Mantena, Weiwei Yang +3
While large transformer models excel in predictive performance, their lack of interpretability restricts their usefulness in high-stakes domains. To remedy this, we propose the Gen…
Vector-ICL: In-context Learning with Continuous Vector Representations
Yufan Zhuang, Chandan Singh, Liyuan Liu +2
Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities on textual data. We explore whether these capabilities can be extended to continuous vecto…
Generative causal testing to bridge data-driven models and scientific theories in language neuroscience
Richard Antonello, Chandan Singh, Shailee Jain +5
Representations from large language models are highly effective at predicting BOLD fMRI responses to language stimuli. However, these representations are largely opaque: it is uncl…
Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
Qingru Zhang, Xiaodong Yu, Chandan Singh +6
Large language models (LLMs) have demonstrated remarkable performance across various real-world tasks. However, they often struggle to fully comprehend and effectively utilize thei…
Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts
Zeliang Zhang, Xiaodong Liu, Hao Cheng +2
By increasing model parameters but activating them sparsely when performing a task, the use of Mixture-of-Experts (MoE) architecture significantly improves the performance of Large…
Crafting Interpretable Embeddings by Asking LLMs Questions
Vinamra Benara, Chandan Singh, John X. Morris +4
Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks. However, their opaqueness and proliferation into scient…
Learning a Decision Tree Algorithm with Transformers
Yufan Zhuang, Liyuan Liu, Chandan Singh +2
Decision trees are renowned for their ability to achieve high predictive performance while remaining interpretable, especially on tabular data. Traditionally, they are constructed…
Rethinking Interpretability in the Era of Large Language Models
Chandan Singh, Jeevana Priya Inala, Michel Galley +2
Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously…
Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
Yanda Chen, Chandan Singh, Xiaodong Liu +4
Large language models (LLMs) often generate convincing, fluent explanations. However, different from humans, they often generate inconsistent explanations on different inputs. For…
Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
Qingru Zhang, Chandan Singh, Liyuan Liu +4
In human-written articles, we often leverage the subtleties of text style, such as bold and italics, to guide the attention of readers. These textual emphases are vital for the rea…
Tree Prompting: Efficient Task Adaptation without Fine-Tuning
John X. Morris, Chandan Singh, Alexander M. Rush +2
Prompting language models (LMs) is the main interface for applying them to new tasks. However, for smaller LMs, prompting provides low accuracy compared to gradient-based finetunin…
Fast-ELECTRA for Efficient Pre-training
Chengyu Dong, Liyuan Liu, Hao Cheng +3
ELECTRA pre-trains language models by detecting tokens in a sequence that have been replaced by an auxiliary model. Although ELECTRA offers a significant boost in efficiency, its p…
ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks
Xiaodong Yu, Hao Cheng, Xiaodong Liu +2
Despite remarkable advancements in mitigating hallucinations in large language models (LLMs) by retrieval augmentation, it remains challenging to measure the reliability of LLMs us…
Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
Suyu Ge, Yunan Zhang, Liyuan Liu +3
In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Differ…
Sparse Backpropagation for MoE Training
Liyuan Liu, Jianfeng Gao, Weizhu Chen
One defining characteristic of Mixture-of-Expert (MoE) models is their capacity for conducting sparse computation via expert routing, leading to remarkable scalability. However, ba…