MaxIM frames incremental memory summarization as an RL reward-shaping problem
A variational mutual-information critic supplies dense rewards so bounded summaries stay predictive of future task targets.
Stories per day · 30 days
Relatedbenchmark1evaluation1gpt-21in-parameter1language-models1llm-agents1memorization1memory1mutual-information1procedural-hallucination1reinforcement-learning1retrieval1speech-recognition1summarization1turkish1turn-taking1
7 stories, newest first · one card per story
Stories tagged #dialogue
TurnTurk-GPT predicts Turkish turn-taking from unpunctuated text
The fine-tuned Turkish GPT-2 beats a multilingual detector, but ties a zero-shot model on unseen speakers.
SKIM stores dialogue turns inside frozen language-model parameters
The model writes self-generated questions as retrieval keys and later answers user questions from parameters alone, with no external store.
DialFork benchmark measures procedural hallucination in dialogue agents
The set has 36,278 forked dialogues, and FlowScore beats semantic similarity across seven encoders.
Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX
Cross-corpus analysis finds gaze patterns modestly correlate with grounding alignment in the MapTask and MUNDEX dialogue corpora.
ECHO: A Matched-Contrast Benchmark for Context-Sensitive Turn-Taking in Full-Duplex Dialogue
ECHO benchmark pairs identical-overlap Chinese dialogue examples with contrasting contexts, revealing most full-duplex systems bias toward yielding the floor.
Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise
Probing finds transformers represent an inferred dialogue partner's expertise in early layers long before it causally influences output.