Field notes
2,343 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.
Click the web, then scroll to zoom
Every note is in the list below. The web of topics draws here once the page has loaded.
45 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on nlp
45 notes, page 2 of 2
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Researchers have created a new benchmark called MM-IssueLoc to evaluate the effectiveness of multimodal repository-level issue localization, which includes visual evidence such as screenshots and logs. Current…
Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution
The paper proposes a new method for detecting text generated by large language models (LLMs) and attributing authorship to them. The method goes beyond just analyzing surface-level linguistic features and instead…
DocMaster: A Hierarchical Structure-Aware System for Document Analysis
DocMaster is a system designed to analyze complex documents while preserving their hierarchical structures such as sections, tables, figures, and equations. It allows users to upload document collections, construct…
Two Axes of LLM Abstention: Answer Correctness and Question Answerability
The paper discusses the issue of language models providing incorrect or unanswerable responses. The author proposes two separate axes for abstention: one for answers the model would get wrong, and another for questions…
Validity of LLMs as data annotators: AMALIA on authority
A study tests the validity of a large language model (LLM), AMALIA, in measuring moral foundation concepts for European Portuguese. The study finds that while AMALIA agrees with human coders on these concepts, it does…
Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs
The researchers evaluate the performance of uncertainty estimation methods across 22 languages in high-, mid-, and low-resource settings using two human-curated question and answer datasets. They compare open and…
Rethinking Indic AI from a Lens of Cultural Heritage Preservation
The paper 'Rethinking Indic AI from a Lens of Cultural Heritage Preservation' discusses how Artificial Intelligence (AI) impacts India's linguistic and cultural foundations, focusing on the challenges and opportunities…
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Researchers propose a new method called Recursive Evidence Replay (RECONTEXT) to improve long-context reasoning in large language models without requiring additional training, memory, or context pruning. RECONTEXT…
From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives
Researchers have developed MAGNET, a framework that generates consistent and coherent long-form narratives by using a unified approach of multi-agent goal-driven storytelling and verification. The system was tested…
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
The research evaluates the issue of data referencing errors (DREs) made by large language models (LLMs) while performing table tasks. The study presents a systematic evaluation of these errors across different models…
MCP Server Architecture Patterns for LLM-Integrated Applications
This paper presents five common architectural patterns of Model Context Protocol (MCP) servers used to integrate large language models with external tools and services, based on an analysis of fifteen independently…
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
Researchers have collected and released a dataset of 4300 coding agent sessions, containing around 350,000 LLM steps and 430,000 tool calls from their own use of Claude Code and Codex. The analysis shows that…
Estimating Commonsense Plausibility through Semantic Shifts
The paper proposes a new method called ComPaSS for evaluating the plausibility of language by measuring changes in semantics when adding common sense-related information to sentences. The method performs better than…
Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement
Researchers have developed a new method called BINEVAL to evaluate the output of large language models (LLMs). Instead of relying on human judgment or lexical metrics, which can be expensive and unreliable, BINEVAL…
Joint Learning of Experiential Rules and Policies for Large Language Model Agents
The paper introduces a new method called Joint Learning of Experiential Rules and Policies (JERP) for large language model agents operating in multi-step interactive environments. The main challenge addressed is…
OpenRCA 2.0: From Outcome Labels to Causal Process Supervision
The paper introduces OpenRCA 2.0, a new benchmark for root cause analysis (RCA) that includes step-wise causal annotations for large language models (LLMs). The benchmark aims to test the capabilities of LLMs in…
Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents
Researchers propose a new memory architecture called REVERIEMEM for book-based role-playing agents to improve the accuracy of the characters' knowledge boundaries and reduce stylistic monotony. They evaluate their…
Weave of Formal Thought
The paper introduces Weave of Formal Thought (WoFT), a new paradigm for large language models that combines syntactic validation with learned structural representations. The proposed approach includes a formal engine…
Grad Detect: Gradient-Based Hallucination Detection in LLMs
The authors present a new method called Grad Detect, which uses the internal gradient structure of Large Language Models (LLMs) during inference to detect hallucinations. This method outperforms confidence-based and…
Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-Commerce
The authors propose a new approach for e-commerce where buyers can pay small amounts of money to access detailed, verified product information through micro-transaction markets. This system aims to reward genuine…
Teaching LLMs String Matching, Backtracking, and Error Recovery to Deduce Bases and Truth Tables for the Combinatorially Exploding Bit Manipulation Puzzles
The paper presents a new approach to solve the NVIDIA Nemotron Model Reasoning Challenge's Bit Manipulation Puzzles, where the goal is to discover hidden rules for transforming binary strings. The approach avoids…
An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.
