## Bar Chart: Turkcell-LLM ### Overview The image is a bar chart comparing the proportion of speaker selections for two types of embedded clauses (Finite and Nominalized) under two different context primes (Shift and Speaker). The chart displays the results for the Turkcell-LLM model. Error bars are included on each bar. ### Components/Axes * **Title:** Turkcell-LLM * **Y-axis:** Proportion of speaker selections, with a scale from 0.00 to 1.00 in increments of 0.25. * **X-axis:** Embedded Clause Type, with two categories: "Finite (shift possible)" and "Nominalized (shift impossible)". * **Legend (top-right):** Context Prime, with two categories: * Shift (0) - represented by a dark blue bar. * Speaker (1) - represented by a light blue bar. ### Detailed Analysis * **Finite (shift possible) Clause:** * Shift (0): Proportion of speaker selections is 0.05, dark blue bar. * Speaker (1): Proportion of speaker selections is 0.19, light blue bar. * **Nominalized (shift impossible) Clause:** * Shift (0): Proportion of speaker selections is 0.03, dark blue bar. * Speaker (1): Proportion of speaker selections is 0.16, light blue bar. ### Key Observations * For both clause types, the "Speaker (1)" context prime results in a higher proportion of speaker selections compared to the "Shift (0)" context prime. * The difference in proportion of speaker selections between "Speaker (1)" and "Shift (0)" is larger for the "Finite (shift possible)" clause type (0.19 vs 0.05) than for the "Nominalized (shift impossible)" clause type (0.16 vs 0.03). * The error bars indicate the variability in the data. ### Interpretation The data suggests that the Turkcell-LLM model is sensitive to the context prime when selecting speakers. Specifically, priming the model with the "Speaker (1)" context leads to a higher likelihood of selecting the speaker, regardless of the type of embedded clause. The difference in performance between the two context primes is more pronounced when the embedded clause allows for a shift in perspective ("Finite (shift possible)"). This could indicate that the model is better at integrating contextual information when the sentence structure allows for more flexibility in interpretation. The error bars provide a measure of the uncertainty associated with these observations.

\n ## Bar Chart: Turkcell-LLM Speaker Selection Proportion ### Overview This bar chart visualizes the proportion of speaker selections for a Turkcell-LLM model, categorized by Embedded Clause Type and Context Prime. The chart displays the average proportion with error bars representing the variability. ### Components/Axes * **Title:** Turkcell-LLM * **X-axis:** Embedded Clause Type. Categories are: "Finite (shift possible)" and "Nominalized (shift impossible)". * **Y-axis:** Proportion of speaker selections. Scale ranges from 0.00 to 1.00, with increments of 0.25. * **Legend:** Located in the top-right corner. * "Shift (0)" - Represented by dark blue color. * "Speaker (1)" - Represented by light blue color. ### Detailed Analysis The chart consists of two sets of bars for each Embedded Clause Type, representing the "Shift" and "Speaker" context primes. Error bars are present on top of each bar, indicating the standard error or confidence interval. **Finite (shift possible):** * **Shift (0):** The dark blue bar has a height of approximately 0.05, with an error bar extending slightly above 0.06. * **Speaker (1):** The light blue bar has a height of approximately 0.19, with an error bar extending from approximately 0.16 to 0.22. **Nominalized (shift impossible):** * **Shift (0):** The dark blue bar has a height of approximately 0.03, with an error bar extending slightly above 0.04. * **Speaker (1):** The light blue bar has a height of approximately 0.16, with an error bar extending from approximately 0.13 to 0.19. ### Key Observations * For both clause types, the "Speaker" context prime (light blue) consistently shows a higher proportion of speaker selections than the "Shift" context prime (dark blue). * The difference between the "Shift" and "Speaker" proportions is more pronounced for the "Finite (shift possible)" clause type than for the "Nominalized (shift impossible)" clause type. * The error bars suggest that the differences observed are statistically significant, although the exact p-values are not provided. ### Interpretation The data suggests that the Turkcell-LLM model is more likely to select the "Speaker" context prime when processing language, regardless of whether a shift in perspective is grammatically possible. The model appears to favor maintaining a consistent speaker perspective. The fact that the difference is more pronounced for "Finite (shift possible)" clauses indicates that the model is sensitive to the grammatical possibility of a shift, but still tends to prioritize the speaker context. This could be due to the model's training data or inherent biases in its architecture. The error bars provide a measure of the variability in the model's responses, suggesting that while there is a clear trend, individual responses may deviate from the average. Further investigation would be needed to determine the underlying reasons for these patterns and to assess the model's performance on other language tasks.

## Bar Chart: Turkcell-LLM - Proportion of Speaker Selections by Embedded Clause Type and Context Prime ### Overview The image is a bar chart titled "Turkcell-LLM" that displays the proportion of speaker selections as a function of two variables: the type of embedded clause and the context prime. The chart compares two embedded clause types ("Finite (shift possible)" and "Nominalized (shift impossible)") under two different context conditions ("Shift (0)" and "Speaker (1)"). ### Components/Axes * **Chart Title:** "Turkcell-LLM" (located at the top-left). * **Y-Axis:** Labeled "Proportion of speaker selections". The scale runs from 0.00 to 1.00, with major tick marks at 0.00, 0.25, 0.50, 0.75, and 1.00. * **X-Axis:** Labeled "Embedded Clause Type". It has two categorical groups: 1. "Finite (shift possible)" 2. "Nominalized (shift impossible)" * **Legend:** Located in the top-right corner, titled "Context Prime". It defines two categories: * **Shift (0):** Represented by a dark blue bar. * **Speaker (1):** Represented by a light blue bar. * **Data Bars:** Four bars in total, two for each x-axis category, with error bars indicating variability (likely standard error or confidence intervals). ### Detailed Analysis The chart presents the following specific data points and trends: **1. Finite (shift possible) Clause Type:** * **Shift (0) Context Prime (Dark Blue Bar):** The proportion is labeled as **0.05**. The bar is very short, indicating a low selection rate. The error bar extends approximately from 0.02 to 0.08. * **Speaker (1) Context Prime (Light Blue Bar):** The proportion is labeled as **0.19**. This bar is significantly taller than its "Shift" counterpart. The error bar extends approximately from 0.12 to 0.25. **2. Nominalized (shift impossible) Clause Type:** * **Shift (0) Context Prime (Dark Blue Bar):** The proportion is labeled as **0.03**. This is the lowest value on the chart. The error bar extends approximately from 0.01 to 0.05. * **Speaker (1) Context Prime (Light Blue Bar):** The proportion is labeled as **0.16**. This bar is taller than its "Shift" counterpart but slightly shorter than the "Finite-Speaker" bar. The error bar extends approximately from 0.10 to 0.22. **Trend Verification:** * For both embedded clause types, the "Speaker (1)" context prime (light blue bars) results in a substantially higher proportion of speaker selections compared to the "Shift (0)" context prime (dark blue bars). * The "Finite" clause type shows slightly higher proportions for both context primes compared to the "Nominalized" clause type (0.05 vs. 0.03 for Shift; 0.19 vs. 0.16 for Speaker). ### Key Observations 1. **Dominant Effect of Context Prime:** The most striking pattern is the large difference between the "Shift" and "Speaker" context primes within each clause type. The "Speaker" prime consistently leads to a higher proportion of speaker selections. 2. **Secondary Effect of Clause Type:** The "Finite (shift possible)" clause type is associated with slightly higher selection proportions than the "Nominalized (shift impossible)" type, regardless of the context prime. 3. **Low Overall Proportions:** All measured proportions are below 0.20, indicating that the event being measured ("speaker selections") occurs less than 20% of the time in all tested conditions. 4. **Variability:** The error bars suggest moderate variability in the measurements, particularly for the "Speaker" context prime conditions. ### Interpretation This chart appears to present results from a psycholinguistic or computational linguistics experiment, likely investigating how language models (hence "LLM" in the title) or human subjects interpret pronouns or reference resolution in different syntactic contexts. * **What the data suggests:** The data strongly suggests that the **context prime** ("Shift" vs. "Speaker") is a major factor influencing the interpretation. A "Speaker" prime biases the system/subject towards selecting the speaker as the referent. The **syntactic structure** of the embedded clause ("Finite" vs. "Nominalized") has a smaller but consistent effect, with finite clauses (where a perspective shift is syntactically possible) leading to slightly more speaker selections than nominalized clauses (where a shift is argued to be impossible). * **How elements relate:** The two independent variables (Context Prime and Clause Type) appear to have an additive effect. The highest proportion (0.19) occurs with the combination that favors speaker reference (Speaker prime + Finite clause), while the lowest (0.03) occurs with the combination that disfavors it (Shift prime + Nominalized clause). * **Notable patterns/anomalies:** The key finding is the interaction—or lack thereof—between the variables. The effect of the context prime seems roughly consistent across both clause types (the light blue bars are both much taller than the dark blue bars). This suggests the context prime's influence is robust and operates independently of the syntactic constraint. The consistently low proportions (all <0.20) might indicate that the "speaker" is not the default or most frequent referent in the experimental setup, or that the task was designed to be difficult.

## Bar Chart: Turkcell-LLM Speaker Selection Proportions ### Overview The chart compares the proportion of speaker selections in two embedded clause types ("Finite" and "Nominalized") under two context primes ("Shift (0)" and "Speaker (1)"). It highlights differences in speaker selection behavior based on clause structure and context. ### Components/Axes - **X-axis**: Embedded Clause Type (Finite, Nominalized) - **Y-axis**: Proportion of speaker selections (0.00–1.00) - **Legend**: - Dark blue: Shift (0) - Light blue: Speaker (1) - **Axis markers**: Tick marks on both axes ### Detailed Analysis - **Finite (shift possible)**: - Shift (0): 0.05 (±0.01) - Speaker (1): 0.19 (±0.03) - **Nominalized (shift impossible)**: - Shift (0): 0.03 (±0.01) - Speaker (1): 0.16 (±0.02) ### Key Observations 1. **Speaker (1) consistently outperforms Shift (0)** in both clause types, with proportions 3.8× higher in Finite and 5.3× higher in Nominalized. 2. **Finite clauses show stronger speaker selection effects** (0.19 vs. 0.16) compared to Nominalized clauses. 3. **Error bars indicate moderate uncertainty**, particularly in the Finite clause's Speaker (1) proportion (±0.03). ### Interpretation The data demonstrates that: - **Context prime type** significantly influences speaker selection, with Speaker (1) driving higher proportions than Shift (0). - **Clause structure** modulates this effect: Finite clauses (which allow shifts) amplify speaker selection more than Nominalized clauses (which block shifts). - The **0.19 vs. 0.16 difference** between Finite and Nominalized Speaker (1) proportions suggests that shift possibility enhances speaker selection by ~18.75%. - The **low Shift (0) proportions** (0.03–0.05) indicate that shift-based selections are rare compared to speaker-driven selections. This pattern implies that Turkcell-LLM's speaker selection mechanism is more sensitive to explicit speaker context (Speaker 1) than to shift possibilities, with clause structure acting as a secondary modulator.