23 stories tagged with #language-processing, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Language Processing"
Inducing Reasoning Primitives from Agent Traces
ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We introduce Reasoning Primitive Ind…
DMF: A Deterministic Memory Framework for Conversational AI Agents
Conversational AI agents require memory systems that are both scalable and semantically coherent across long interaction horizons. Existing approaches rely predominantly on large l…
Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models
Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy…
A Dataset of Robot-Patient and Doctor-Patient Medical Dialogues for Spoken Language Processing Tasks
Large Language Models (LLMs) have brought huge improvements to Artificial Intelligence (AI), which can be applied to general-purpose tasks. However, their application to textual or…
From Norms to Indicators (N2I-RAG): An Agentic Retrieval-Augmented Generation Framework for Legal Indicator Computation
Computing legal indicators from normative texts is a key task in legal monitoring and policy evaluation, but presents significant challenges due to the complexity, scale, and inter…
PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
The emergence of Large Reasoning Language Models (LRMs) has paved the way for tackling complex reasoning tasks through test-time scaling by generating long-form Chain-of-Thought (C…
Parallel Context Compaction for Long-Horizon LLM Agent Serving
Long-horizon LLM agents accumulate growing conversation histories that eventually exceed the model's context window. Context compaction via LLM-based summarization keeps the conver…
Seeing without Looking: Do Vision-Language Benchmarks Really Test Vision?
Benchmark accuracy is often implicitly assumed to reflect grounded visual understanding in vision-language models (VLMs), yet it remains unclear to what extent such scores truly re…
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewar…
SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction
Joint Entity and Relation Extraction (JERE) is highly susceptible to weak generalization due to low-quality training data. Data augmentation is a common strategy to enhance model…
Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding
Real-world time series come with text: metadata, descriptions, news, reports. Yet time series foundation models process numerical sequences in isolation, and the multimodal text-an…
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks through demonstrations, yet it suffers from escalating inference costs as context length increas…
The Ettin Reranker Family
We’re on a journey to advance and democratize artificial intelligence through open source and open science.…
AgentNLQ: A General-Purpose Agent for Natural Language to SQL
Natural language to SQL (NL2SQL) conversion is an important problem for researchers and enterprises due to the ubiquitous importance of relational databases in broad-ranging practi…
Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method
Retrieving relevant tables from extensive databases for a given natural language query is essential for accurately answering questions in tasks such as text-to-SQL. Existing table …
HyperPersona: A Multi-Level Hypergraph Framework for Text-Based Automatic Personality Prediction
As a modern commodity, language has become a vast repository of socially and psychologically significant traits and concepts, reflecting the ways people encode pattern of thoughts,…
Fixing LLM Writing with Distribution Fine Tuning
Technical Report: How Distribution Fine Tuning (DFT) improves LLM writing quality…
Domain-Independent Game Abstraction using Word Embedding Techniques
Many games of interest in the real world are often intractably large, thereby necessitating the use of game abstraction to shrink them in size, typically by many magnitudes. Over t…
Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation
Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios su…
Teaching an AI to Pick Its Own Brain: Building Adaptive Model Routing
Part 2 of the crab-bot series. If you missed Part 1, start here. The Problem Nobody...…
The Streaming Latency Tradeoff: Why Some TTS Models Lose Accuracy in Real Time
Streaming TTS loses 5-20x context vs batch processing, causing pronunciation failures on alphanumeric IDs. Learn when to choose batch over real-time synthesis.…
What Are Tokens and Temperature in AI Models?
A practical explanation of tokens, max tokens, and temperature for managers and engineers using Claude, Gemini, Llama, Gemma, and Qwen.…