Papers by Bryan Kian Hsiang Low

9 papers
Uncovering Scaling Laws for Large Language Models via Inverse Problems (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have achieved remarkable success across diverse domains.
Approach: inverse problems can efficiently uncover scaling laws that guide the building of LLMs, authors argue . authors propose brute-force approaches to improve LLM training costs due to high costs .
Outcome: This paper advocates that inverse problems can efficiently uncover scaling laws that guide the building of LLMs to achieve the desirable performance with significantly better cost-effectiveness.
TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding (2025.acl-long)

Copied to clipboard

Challenge: Existing methods that optimize for a single request or a group of requests as a whole only select the most promising draft tokens to be accepted when verified in parallel.
Approach: They propose a method that optimizes the total throughput of batch speculative decoding in multi-request settings by actively selecting the most promising draft tokens to be accepted when verified in parallel.
Outcome: The proposed method outperforms baseline speculative decoding and existing methods that dynamically select draft tokens, leading to a more efficient batch inference in large language models.
EULoInf: Efficient Hessian-Free Entropy Based Uncertainty-Aware Data Influence Approximation (2026.findings-acl)

Copied to clipboard

Challenge: Extensive studies show that the effectiveness of fine-tuning heavily relies on the quality of training data.
Approach: They propose a framework that approximates influence via uncertainty and gradient based validation loss lookahead.
Outcome: The proposed framework matches or outperforms prior methods across diverse tasks and LLM architectures while reducing computational time and memory usage by over 50%.
Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning Tasks (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for large language models rely on sequential queries . however, existing methods rely heavily on sequential querying .
Approach: They propose a training-free framework that transforms a single LLM into an effective inference-time ensemble.
Outcome: The proposed framework outperforms existing models on reasoning benchmarks, such as MATH, and improves on a DIPPER ensemble of three Qwen2-MATH-1.5B instances.
WASA: WAtermark-based Source Attribution for Large Language Model-Generated Data (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have impressive performance but intellectual property concerns are looming . a framework that can be used to perform source attribution for LLMs can be developed.
Approach: They propose a framework that enables an LLM to generate synthetic texts with embedded watermarks that contain information about their source.
Outcome: The proposed framework achieves source attribution accuracy and robustness against adversaries.
Prompting the Unknown: Understanding Response Uncertainty in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models are widely used in decision-making across diverse domains.
Approach: They propose a prompt-response concept model that explains the relationship between the amount of task-relevant information provided in the prompt and the LLM-generated response uncertainty by identifying four sources of response uncertainty.
Outcome: The proposed model shows that the amount of information provided in the prompt influences the LLM-generated response uncertainty.
Waterfall: Scalable Framework for Robust Text Watermarking and Provenance for LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Existing text watermarking methods are not robust enough against paraphrasing attacks . existing methods lack robustness to paraphrases and are not scalable to millions of users .
Approach: They propose a training-free framework for robust and scalable text watermarking . they propose to use large language models as paraphrasers and a combination of techniques .
Outcome: The proposed framework improves scalability, verifiability and computational efficiency compared to existing methods.
Position Paper: Data-Centric AI in the Age of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: a paper proposes a data-centric perspective of AI research, focusing on large language models.
Approach: They propose a data-centric viewpoint of AI research, focusing on large language models . they propose four scenarios centered around data, including data curation, attribution, knowledge transfer .
Outcome: The proposed research focuses on large language models with data centric benchmarks . the proposed benchmarks can be used to develop new data curation methods .
Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graph for Retrieval-Augmented Generation (2026.eacl-long)

Copied to clipboard

Challenge: Standard unstructured RAG methods rely on embedding-similarity matching and lack any general mechanism to encode or exploit chronological information.
Approach: They propose a retrieval-augmented generation framework that integrates a document retrieval generator with an exter-nal document retriever to enhance the model's accuracy.
Outcome: The proposed framework outperforms state-of-the-art unstructured and KG-based RAG frameworks on causal and character consistency queries.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations