Natural Language Processing

Typed-RAG enhances non-factoid QA by type-aware decomposition, refining retrieval and generation for nuanced, user-aligned answers.

A comprehensive survey on evaluation methodologies for LLM-based agents, analyzing benchmarks and frameworks across key dimensions like capabilities, applications, and generalist performance.

LLMs survey: Model, output, and prompt-based strategies for efficient reasoning, mitigating ‘overthinking’ for faster, cheaper, and real-world applications.

MathFusion: Instruction Fusion enhances LLM’s math problem-solving!

New dataset bridges fabricated claims with humor for spotting online deception!

CaKE: Editing LLMs to Enhance Knowledge Generalization Across Reasoning Tasks.

BIGO(Bench) can help LLMs generate code with controlled time/space complexity, addressing the gap in current evaluations and encouraging further exploration.

A new test-time method, Temporal Consistency, is introduced to improve LLM reasoning by leveraging iterative self-reflection.

Pensez: Strategic fine-tuning beats massive data for superior reasoning in French LLMs, challenging conventional wisdom.

Φ-Decoding: Adaptive foresight sampling balances inference-time exploration and exploitation for better LLM reasoning.

This research explores how well LLM uncertainty measures align with human uncertainty, finding Bayesian and top-k entropy measures show promise.

GKG-LLM: Unifying Knowledge Graph Construction with a novel 3-stage framework, empowering domain adaptation & resource efficiency.

LRMs transform MT with reasoning, handling context, culture, and nuance for better translations.

Light-R1: Trains long COT models from scratch using curriculum SFT, DPO, and RL, achieving SOTA performance and strong generalization with limited resources.

PLM retrievers overrate low-perplexity docs, causing source bias. This paper reveals the causal effect & offers a fix!

BIASEDIT: Efficiently debiasing language models via lightweight network edits!

SEAP: Unlock LLM brainpower w/ training-free sparse expert activation pruning! Boost efficiency, keep accuracy. Optimize LLMs now!

WILDIFEVAL: Instruction Following in the Wild.

LLMs as MT encoders enhance efficiency & generalization!

WritingBench: A new benchmark for generative writing evaluation, enhancing LLMs across diverse domains.